Circuit Tracing: Revealing Computational Graphs in Language Models
Emmanuel Ameisen, Jack Lindsey, Adam Pearce, Wes Gurnee, Nicholas L. Turner, Brian Chen, … (+21 more) — 2025-03-27 — Anthropic — Transformer Circuits Thread
Summary
Introduces cross-layer transcoders (CLTs) and attribution graphs methodology for understanding language model computations by tracing computational steps through an interpretable replacement model, with extensive validation and applications to both toy models and Claude 3.5 Haiku.
Key Result
Cross-layer transcoders match the underlying model’s next-token completion on 50% of diverse pretraining prompts while enabling interpretable attribution graphs that trace feature-to-feature interactions through frozen attention patterns.
Source
- Link: https://transformer-circuits.pub/2025/attribution-graphs/methods.html
- Listed in the Shallow Review of Technical AI Safety 2025 under 2 agenda(s):
- anthropic — Labs (giant companies)
- sparse-coding — White-box safety (i.e. Interpretability)