Bartosz Cywiński

bcywinski

AI & ML interests

Mechanistic Interpretability

Recent Activity

updated a collection 2 days ago
Eliciting Secret Knowledge from Language Models
updated a collection 2 days ago
gemma-2-9b-it-taboo-nonmix
updated a collection 2 days ago
gemma-2-9b-it-taboo-nonmix
View all activity

Organizations

None yet