72 citations · 81 across the 9 of their papers we have counts for
10 papers
Interpreting Language Model Parameters
Lucius Bushnaq, Dan Braun, Oliver Clive-Griffin +5
Mechanistic interpretability aims to uncover how neural networks use their parameters to implement their impressive neural algorithms. Although previous work has uncovered substant…
Targeted Recovery of Weight-Space Mechanisms From Neural Networks
Antoine Vigouroux, Lee Sharkey
Parameter decomposition (PD) decomposes neural networks into interpretable computational components that faithfully reflect the original network's operations. However, scaling PD t…
Stochastic Parameter Decomposition
Lucius Bushnaq, Dan Braun, Lee Sharkey
A key step in reverse engineering neural networks is to decompose them into simpler parts that can be studied in relative isolation. Linear parameter decomposition -- a framework t…
AI Behind Closed Doors: a Primer on The Governance of Internal Deployment
Charlotte Stix, Matteo Pistillo, Girish Sastry +6
The most advanced future AI systems will first be deployed inside the frontier AI companies developing them. According to these companies and independent experts, AI systems may re…
Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video
Sonia Joseph, Praneet Suresh, Lorenz Hufe +7
Robust tooling and publicly available pre-trained models have helped drive recent advances in mechanistic interpretability for language models. However, similar progress in vision…
Identifying Sparsely Active Circuits Through Local Loss Landscape Decomposition
Brianna Chrisman, Lucius Bushnaq, Lee Sharkey
Much of mechanistic interpretability has focused on understanding the activation spaces of large neural networks. However, activation space-based approaches reveal little about the…
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Dan Braun, Lucius Bushnaq, Stefan Heimersheim +2
Mechanistic interpretability aims to understand the internal mechanisms learned by neural networks. Despite recent progress toward this goal, it remains unclear how best to decompo…
Open Problems in Mechanistic Interpretability
Lee Sharkey, Bilal Chughtai, Joshua Batson +26
Mechanistic interpretability aims to understand the computational mechanisms underlying neural networks' capabilities in order to accomplish concrete scientific and engineering goa…
Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
Dan Braun, Jordan Taylor, Nicholas Goldowsky-Dill +1
Identifying the features learned by neural networks is a core challenge in mechanistic interpretability. Sparse autoencoders (SAEs), which learn a sparse, overcomplete dictionary t…
Black-Box Access is Insufficient for Rigorous AI Audits
Stephen Casper, Carson Ezell, Charlotte Siegmann +18
External audits of AI systems are increasingly recognized as a key mechanism for AI governance. The effectiveness of an audit, however, depends on the degree of access granted to a…