CallumMcDougall

TLDR * The Google DeepMind mech interp team is releasing Gemma Scope 2: a suite of SAEs & transcoders trained on the Gemma 3 model family * Neuronpedia demo here, access the weights on HuggingFace here, try out the Colab notebook tutorial here [1] * Key features of this relative...

Executive Summary * Over the past year, the Google DeepMind mechanistic interpretability team has pivoted to a pragmatic approach to interpretability, as detailed in our accompanying post [1] , and are excited for more in the field to embrace pragmatism! In brief, we think that: * It is crucial to...

Executive Summary * The Google DeepMind mechanistic interpretability team has made a strategic pivot over the past year, from ambitious reverse-engineering to a focus on pragmatic interpretability: * Trying to directly solve problems on the critical path to AGI going well [[1]] * Carefully choosing problems according to our comparative...

Lewis Smith*, Sen Rajamanoharan*, Arthur Conmy, Callum McDougall, Janos Kramar, Tom Lieberum, Rohin Shah, Neel Nanda * = equal contribution The following piece is a list of snippets about research from the GDM mechanistic interpretability team, which we didn’t consider a good fit for turning into a paper, but which...

Adam Karvonen*, Can Rager*, Johnny Lin*, Curt Tigges*, Joseph Bloom*, David Chanin, Yeu-Tong Lau, Eoin Farrell, Arthur Conmy, Callum McDougall, Kola Ayonrinde, Matthew Wearden, Samuel Marks, Neel Nanda *equal contribution TL;DR * We are releasing SAE Bench, a suite of 8 diverse sparse autoencoder (SAE) evaluations including unsupervised metrics and...

Epistemic status - self-evident. In this post, we interpret a small sample of Sparse Autoencoder features which reveal meaningful computational structure in the model that is clearly highly researcher-independent and of significant relevance to AI alignment. Motivation Recent excitement about Sparse Autoencoders (SAEs) has been mired by the following question:...

This is a post to officially announce the sae-vis library, which was designed to create feature dashboards like those from Anthropic's research. Summary There are 2 types of visualisations supported by this library: feature-centric and prompt-centric. The feature-centric vis is the standard from Anthropic’s post, it looks like the image...