Phillip Guo

PhillipGuo

AI & ML interests

Interp, Unlearning, Editing

Recent Activity

updated a model about 1 hour ago
PhillipGuo/gemma-2-sae-masked-gd-mc-fullrank
updated a model about 21 hours ago
PhillipGuo/gemma-2-gd-mc-fullrank
updated a dataset 3 days ago
PhillipGuo/wmdp-deduped
View all activity

Organizations

Truthfulness & Deception Research Team's profile picture quirky-lats-at-mats's profile picture LLM Latent Adversarial Training's profile picture