@DanKornas: Turn a model output into an inspectable attribution graph instead of guessing which internal features contributed. circ…

X AI KOLs Timeline Tools

Summary

circuit-tracer is a Python library that helps interpretability researchers map model computations by calculating direct effects between transcoder features and output logits, then visualizing them as an interactive attribution graph.

Turn a model output into an inspectable attribution graph instead of guessing which internal features contributed. circuit-tracer is a Python library for interpretability researchers and ML builders who want to examine circuits built from pretrained transcoders. It helps you map model computations by calculating direct effects between transcoder features, error nodes, input tokens, and output logits, then turning those results into an attribution graph. Key features: • Circuit attribution – computes feature-to-feature and feature-to-logit direct effects. • Interactive visualization – serves graphs locally for browsing, pinning, grouping, and annotation. • Feature interventions – sets transcoder features to chosen values so you can observe output changes. • Multiple workflows – runs through Neuronpedia, Python or Jupyter, and a command-line interface. • Practical demos – includes tutorials for Gemma 2, Llama 3.2, attribution targets, and interventions. It’s open-source (MIT license). Link in the reply
Original Article
View Cached Full Text

Cached at: 07/31/26, 12:45 AM

Turn a model output into an inspectable attribution graph instead of guessing which internal features contributed.

circuit-tracer is a Python library for interpretability researchers and ML builders who want to examine circuits built from pretrained transcoders.

It helps you map model computations by calculating direct effects between transcoder features, error nodes, input tokens, and output logits, then turning those results into an attribution graph.

Key features: • Circuit attribution – computes feature-to-feature and feature-to-logit direct effects. • Interactive visualization – serves graphs locally for browsing, pinning, grouping, and annotation. • Feature interventions – sets transcoder features to chosen values so you can observe output changes. • Multiple workflows – runs through Neuronpedia, Python or Jupyter, and a command-line interface. • Practical demos – includes tutorials for Gemma 2, Llama 3.2, attribution targets, and interventions.

It’s open-source (MIT license).

Link in the reply

Similar Articles

Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations

arXiv cs.AI

Introduces Tokengeist, a method for tracing attribution across multiple turns in agentic conversations, revealing that flat attribution methods fail and that recursive dependency graphs are needed, achieving 90% source recall on a new benchmark (MTCABench) of 3,845 target spans.

LLMs Can Annotate Attribution Graphs

arXiv cs.LG

The paper presents a simple pipeline that uses LLMs to automatically group features into supernodes in attribution graphs, matching human annotator interpretability and recovering intermediate hop supernodes in a two-hop task.