Top postsTop post
TL;DR: We're excited to announce the ninth iteration of ARENA (Alignment Research Engineer Accelerator), a 4-5 week ML bootcamp with a focus on AI safety! Our mission is to provide talented individuals with the ML engineering skills, community, and confidence to contribute directly to technical AI safety. ARENA 9.0 will...
This is the fifth in a series of informal research updates from the Google DeepMind Language Model Interpretability team, in interpretability and adjacent areas. The fourth post can be found here. Thanks to Chloe Li for feedback on this post! TLDR: Via adapting the methods of Marks et al and...
TLDR This is a post announcing a lot of new ARENA material I've been working on for a while, which is now available for study here (currently on the alignment-science branch, but planned to be merged into main this Sunday). There's a set of exercises (each one contains about 1-2...
TL;DR: We're excited to announce the eighth iteration of ARENA (Alignment Research Engineer Accelerator), a 4-5 week ML bootcamp with a focus on AI safety! Our mission is to provide talented individuals with the ML engineering skills, community, and confidence to contribute directly to technical AI safety. ARENA 8.0 will...
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...
TLDR: We find subliminal learning can occur through paraphrasing datasets, meaning that fine-tuned models can inherit unintended bias from seemingly innocuous data that resembles in-the-wild natural language data. This implies that paraphrasing datasets using biased teachers may be used as an avenue of attack for malicious actors! While the recent...
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...