CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability

By Pratinav Seth · Paper · cs.LG

Circuit analysis can support not only model explanation but also downstream interventions such as pruning, editing, steering, and selective fine-tuning. However, conducting such analyses currently requires stitching together separate implementations for discovery, evaluation, and

Cs.lg

View original

HomeResourceLoading…