- sae_20251024T213152_20480concepts_top32_lr5e-05 Upload trained model sae_20251024T213152_20480concepts_top32_lr5e-05
- 1.52 kB initial commit
- epoch_0001.pt210 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0002.pt210 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0003.pt210 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0004.pt210 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0005.pt210 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0006.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0007.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0008.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0009.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0010.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0011.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0012.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0013.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0014.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0015.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0016.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0017.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0018.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0019.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0020.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0021.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0022.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0023.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0024.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0025.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0026.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0027.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0028.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0029.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - epoch_0030.pt315 MB
Detected Pickle imports (14)
- "torch.nn.modules.container.ModuleList",
- "torch.nn.modules.linear.Linear",
- "__builtin__.set",
- "torch.nn.modules.activation.ReLU",
- "overcomplete.sae.modules.MLPEncoder",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "collections.OrderedDict",
- "torch.nn.modules.container.Sequential",
- "overcomplete.sae.dictionary.normalize_l2",
- "torch._utils._rebuild_parameter",
- "sparta.overcomplete.overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.FloatStorage",
- "overcomplete.sae.dictionary.DictionaryLayer"
xetUpload trained model sae_20251024T213152_20480concepts_top32_lr5e-05 - 1.37 kB xetUpload info.pt with huggingface_hub
- model.pt210 MB
Detected Pickle imports (14)
- "torch._utils._rebuild_tensor_v2",
- "__builtin__.set",
- "overcomplete.sae.dictionary.normalize_l2",
- "collections.OrderedDict",
- "torch.FloatStorage",
- "overcomplete.sae.modules.MLPEncoder",
- "torch.nn.modules.activation.ReLU",
- "torch._utils._rebuild_parameter",
- "torch.nn.modules.linear.Identity",
- "overcomplete.sae.batchtopk_sae.BatchTopKSAE",
- "torch.nn.modules.container.ModuleList",
- "overcomplete.sae.dictionary.DictionaryLayer",
- "torch.nn.modules.container.Sequential",
- "torch.nn.modules.linear.Linear"
xetUpload model.pt with huggingface_hub