165 citations · 287 across the 6 of their papers we have counts for
6 papers
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…
Large Scale Qualitative Evaluation of Generative Image Model Outputs
Yannick Assogba, Adam Pearce, Madison Elliott
Evaluating generative image models remains a difficult problem. This is due to the high dimensionality of the outputs, the challenging task of representing but not replicating trai…
Acquisition of Chess Knowledge in AlphaZero
Thomas McGrath, Andrei Kapishnikov, Nenad Tomašev +5
What is learned by sophisticated neural network agents such as AlphaZero? This question is of both scientific and practical interest. If the representations of strong neural networ…
An Interpretability Illusion for BERT
Tolga Bolukbasi, Adam Pearce, Ann Yuan +4
We describe an "interpretability illusion" that arises when analyzing the BERT model. Activations of individual neurons in the network may spuriously appear to encode a single, sim…
Visualizing and Measuring the Geometry of BERT
Andy Coenen, Emily Reif, Ann Yuan +4
Transformer architectures show significant promise for natural language processing. Given that a single pretrained model can be fine-tuned to perform well on many different tasks,…