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 “Entity Recognition and Hallucinations” · whole deck
Entity Recognition and Hallucinations
- What “default” circuit did Lindsey et al. find behind declining to answer?In assistant dialogues, “can’t answer” features are active by default, and unfamiliar names push them further. For entities the model knows (e.g. Michael Jordan), “known entity/answer” features inhibit them so it answers. For an unknown name (“Michael Batkin”) nothing inhibits them, so it declines.
- Lindsey et al., 2025, On the Biology of a Large Language Model (Transformer Circuits Thread), Entity Recognition and Hallucinations
- According to Lindsey et al., how do hallucinations arise?From misfires of the known-entity circuit: a familiar name (e.g. Andrej Karpathy, asked for one of his papers) activates “known answer” features enough to suppress “can’t answer” even though the specific fact is missing, so the model guesses plausibly. Artificially activating these features on an unknown name likewise causes hallucination.
- Lindsey et al., 2025, On the Biology of a Large Language Model (Transformer Circuits Thread), Entity Recognition and Hallucinations
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