Top postsTop post
Josh Engels
604
Ω
34
6
10
Code and data can be found here Executive Summary * We use data from Zhang et al. (2025) to measure LLM values. We find that our value metric can sometimes predict LLM behaviors on a test distribution in non-safety-relevant settings, but it is not super consistent. * In Zhang et...
This project is an extension of work done for Neel Nanda’s MATS 9.0 Training Phase. Neel Nanda and Josh Engels advised the project. Initial work on this project was done with David Vella Zarb. Thank you to Arya Jakkli, Paul Bogdan, and Monte MacDiarmid for providing feedback on the post...
Authors: Bartosz Cywinski*, Bart Bussmann*, Arthur Conmy**, Joshua Engels**, Neel Nanda**, Senthooran Rajamanoharan** * primary contributors ** advice and mentorship TL;DR We study a simple latent reasoning LLM on math tasks using standard mechanistic interpretability techniques to see whether the latent reasoning process (i.e., vector-based chain of thought) is interpretable....
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...
Authors: Bartosz Cywinski*, Bart Bussmann*, Arthur Conmy**, Neel Nanda**, Senthooran Rajamanoharan**, Joshua Engels** * equal primary contributor, order determined via coin flip ** equal advice and mentorship, order determined via coin flip > “Tampering alert: The thought "I need to provide accurate, helpful, and ethical medical advice" is not my...
Summary Reproducing a result from recent work, we study a Gemma 3 12B instance trained to take risky or safe options; the model can then report its own risk tolerance. We find that: * Applying LoRA to a single MLP is enough to reproduce the behavior * The single LoRA...