Backdoors research

AI & ML interests

Mechinterp, AI safety

Recent Activity

abir-hr196  authored a paper about 19 hours ago

Activation Space Interventions Can Be Transferred Between Large Language Models

abir-hr196  authored a paper about 20 hours ago

TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research

amirabdullah19852020  authored a paper over 1 year ago

Beyond Training Objectives: Interpreting Reward Model Divergence in Large Language Models

View all activity

Team members 6