On the Biology of a Large Language Model
Lindsey et al., 2025, On the Biology of a Large Language Model (Transformer Circuits Thread)
Subscriber deck — free during early access
2 cards in “Method Overview” · whole deck
Method Overview
- What is a “replacement model” in Lindsey et al.’s method, and what are its error nodes?A cross-layer transcoder (CLT) replaces the model’s MLP neurons with sparse, more interpretable features that approximately reproduce its activations. For one prompt, error nodes hold what the CLT fails to reconstruct, and attention patterns are copied from the real model. This is the “local replacement model”.
- Lindsey et al., 2025, On the Biology of a Large Language Model (Transformer Circuits Thread), Method Overview
- What is an attribution graph, and how are its claims checked?A graph of the features active on one prompt and the causal edges between them that lead to an output token, pruned to the important parts, with related features grouped by hand into “supernodes”. Since it describes the replacement model, its hypotheses are tested by interventions on the real model, e.g. inhibiting a supernode and observing downstream features and outputs.
- Lindsey et al., 2025, On the Biology of a Large Language Model (Transformer Circuits Thread), Method Overview
Source
- Jack Lindsey, Wes Gurnee, Emmanuel Ameisen, Brian Chen, Adam Pearce, Nicholas L. Turner, Craig Citro, David Abrahams, Shan Carter, Basil Hosmer, Jonathan Marcus, Michael Sklar, Adly Templeton, Trenton Bricken, Callum McDougall, Hoagy Cunningham, Thomas Henighan, Adam Jermyn, Andy Jones, Andrew Persic, Zhenyi Qi, T. Ben Thompson, Sam Zimmerman, Kelley Rivoire, Thomas Conerly, Chris Olah and Joshua Batson. 2025. On the Biology of a Large Language Model. In Transformer Circuits Thread. https://transformer-circuits.pub/2025/attribution-graphs/biology.html