Hugging Face's logo
colored_dye's picture
4

colored_dye

colored-dye
Reza22farokhi's profile picture rakibuls-net's profile picture
·

AI & ML interests

mechanistic interpretability, training data attribution, representation steering

Recent Activity

upvoted a paper 1 day ago
PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
upvoted a paper 1 day ago
Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
updated a dataset 1 day ago
colored-dye/concept500-contrastive
View all activity

Organizations

None yet