1

Progress measures for grokking via mechanistic interpretability
We fully reverse engineer 32 small transformers trained on modular addition and use this understanding to study grokking.
Neel Nanda, Lawrence Chan, Tom Lieberum, Jess Smith, Jacob Steinhardt
PDF Cite arXiv
Progress measures for grokking via mechanistic interpretability
Adversarial Training for High-Stakes Reliability
We study the limits of adversarial training on a injury classification task using a variety of attacks including a new saliency map–based snippet rewrite tool to assist our human adversaries. While advesarial training was not able to eliminate all in-distribution failures, it did increase robustness to the adversarial attacks that we trained on.
Daniel M Ziegler, Seraphina Nix, Lawrence Chan, Tim Bauman, Peter Schmidt-Nielsen, Tao Lin, Adam Scherlis, Noa Nabeshima, Ben Weinstein-Raun, Daniel de Haas, others
PDF Cite Slides arXiv
Optimal Cost Design for Model Predictive Control
Avik Jain, Lawrence Chan, Daniel S Brown, Anca D Dragan
Cite
The assistive multi-armed bandit
We study the problem of learning to assist a human who is themselves learning about their preferences.
Lawrence Chan, Dylan Hadfield-Menell, Siddhartha Srinivasa, Anca Dragan
PDF Cite Code arXiv