collaborators

5 papers

cs.LG2026

Building Production-Ready Probes For Gemini

János Kramár, Joshua Engels, Zheng Wang +4

Frontier language model capabilities are improving rapidly. We thus need stronger mitigations against bad actors misusing increasingly powerful systems. Prior work has shown that a…

cs.LG2024

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.LG2024

On scalable oversight with weak LLMs judging strong LLMs

Zachary Kenton, Noah Y. Siegel, János Kramár +8

Scalable oversight protocols aim to enable humans to accurately supervise superhuman AI. In this paper we study debate, where two AI's compete to convince a judge; consultancy, whe…

cs.LG2024

Improving Dictionary Learning with Gated Sparse Autoencoders

Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith +5

Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by find…

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…