Mechanistic Interpretability Benchmark

AI & ML interests

Principled evaluation of mechanistic interpretability methods.

Recent Activity

atticusg  authored a paper 3 months ago

Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations

AdamBelfki  authored a paper 5 months ago

NNsight and NDIF: Democratizing Access to Foundation Model Internals

amueller  authored a paper 5 months ago

NNsight and NDIF: Democratizing Access to Foundation Model Internals

View all activity

Team members 12