Transformer Circuit Faithfulness Metrics are not Robust
Interpretability
Existing circuits in the mechanistic interpretability literature may not be as faithful as reported. Current circuit faithfulness scores reflect both the methodological choices of researchers and the actual components of the circuit.
July 10, 2024
Date Range
News
No items found.
Research
Our research explores a portfolio of high-potential agendas.
Events
Our events bring together global leaders in AI.
Programs
Our programs build the field of trustworthy and secure AI
