Lawrence Chan
Lawrence Chan
Home
Publications
1
Mathematical Models of Computation in Superposition
We formally study what sparse circuits neural networks can represent and compute in superposition – that is, using sparse features respresented near-orthogonally in a high-dimensional space. We show that not only can ReLU MLPs perform more computation at a fixed given width by placing features in superposition, but also that they can maintain superposition through multiple layers.
Kaarel Hänni
,
Jake Mendel
,
Dmitry Vaintrob
,
Lawrence Chan
PDF
Cite
arXiv
OpenReview
Compact Proofs of Model Performance via Mechanistic Interpretability
We use mechanistic interpretability to general compact formal guarantees on model performance on a toy Max-of-K task. We find that shorter proofs seem to require more mechanistic understanding and more faithful mechanistic understanding leads to tighter performance bounds. We identify compounding structureless noise as a key challenge for the proofs approach.
Jason Gross
,
Rajashree Argawal
,
Thomas Kwa
,
Euan Ong
,
Chun Hei Yip
,
Alex Gibson
,
Soufiane Noubir
,
Lawrence Chan
PDF
Cite
arXiv
OpenReview
A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations
We reverse engineer small transformers trained on group composition and use our understanding to explore the universality hypothesis.
Bilal Chughtai
,
Lawrence Chan
,
Neel Nanda
PDF
Cite
arXiv
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
The alignment problem from a deep learning perspective
We argue that AGIs trained in similar ways as today’s most capable models could learn to act deceptively to receive higher reward; learn internally-represented goals which generalize beyond their training distributions; and pursue those goals using power-seeking strategies.
Richard Ngo
,
Lawrence Chan
,
Sören Mindermann
PDF
Cite
arXiv
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
Cite
×