6 papers
Verbalizable Representations Form a Global Workspace in Language Models
Wes Gurnee, Nicholas Sofroniew, Adam Pearce +13
Out of everything the human brain processes, only a small fraction is consciously accessible, in the sense of being available for verbal report, deliberate control, and flexible re…
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
Adly Templeton, Tom Conerly, Jonathan Marcus +23
We demonstrate that sparse autoencoders can extract interpretable features from Claude 3 Sonnet, a production-scale language model, addressing the open question of whether dictiona…
Emotion Concepts and their Function in a Large Language Model
Nicholas Sofroniew, Isaac Kauvar, William Saunders +13
Large language models (LLMs) sometimes appear to exhibit emotional reactions. We investigate why this is the case in Claude Sonnet 4.5 and explore implications for alignment-releva…
When Models Manipulate Manifolds: The Geometry of a Counting Task
Wes Gurnee, Emmanuel Ameisen, Isaac Kauvar +4
Language models can perceive visual properties of text despite receiving only sequences of tokens-we mechanistically investigate how Claude 3.5 Haiku accomplishes one such task: li…
Auditing language models for hidden objectives
Samuel Marks, Johannes Treutlein, Trenton Bricken +32
We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objecti…
Open Problems in Mechanistic Interpretability
Lee Sharkey, Bilal Chughtai, Joshua Batson +26
Mechanistic interpretability aims to understand the computational mechanisms underlying neural networks' capabilities in order to accomplish concrete scientific and engineering goa…