most citedEvaluating Frontier Models for Dangerous Capabilities

11 citations · 21 across the 5 of their papers we have counts for

collaborators

5 papers

cs.LG20241 cited

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Tom Lieberum, Senthooran Rajamanoharan, Arthur Conmy +7

Sparse autoencoders (SAEs) are an unsupervised method for learning a sparse decomposition of a neural network's latent representations into seemingly interpretable features. Despit…

cs.LG20243 cited

Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Senthooran Rajamanoharan, Tom Lieberum, Nicolas Sonnerat +4

Sparse autoencoders (SAEs) are a promising unsupervised approach for identifying causally relevant and interpretable linear features in a language model's (LM) activations. To be u…

cs.LG202411 cited

Evaluating Frontier Models for Dangerous Capabilities

Mary Phuong, Matthew Aitchison, Elliot Catt +24

To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new "dangerous capability" evalu…

cs.LG2024

AtP*: An efficient and scalable method for localizing LLM behaviour to components

János Kramár, Tom Lieberum, Rohin Shah +1

Activation Patching is a method of directly computing causal attributions of behavior to model components. However, applying it exhaustively requires a sweep with cost scaling line…

cs.LG20236 cited

Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla

Tom Lieberum, Matthew Rahtz, János Kramár +4

\emph{Circuit analysis} is a promising technique for understanding the internal mechanisms of language models. However, existing analyses are done in small models far from the stat…