CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability
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 intervention, as well as hand-authoring the contrastive prompts required by many discovery methods. This fragmentation makes methods difficult to compare and limits their application beyond canonical tasks. We introduce CircuitKIT, a source-available library that connects the circuit-analysis workflow through a typed,
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via arxiv author · 85%Pratinav Seth →
“CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability”
- LinkedLinked via arxiv author · 85%Hem Gosalia →
“CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability”
- LinkedLinked via arxiv author · 85%Aditya Kasliwal →
“CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability”
- LinkedLinked via arxiv author · 85%Vinay Kumar Sankarapu →
“CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability”