9 citations · 16 across the 7 of their papers we have counts for
7 papers
Detecting Strategic Deception Using Linear Probes
Nicholas Goldowsky-Dill, Bilal Chughtai, Stefan Heimersheim +1
AI models might use deceptive strategies as part of scheming or misaligned behaviour. Monitoring outputs alone is insufficient, since the AI might produce seemingly benign outputs…
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…
Towards evaluations-based safety cases for AI scheming
Mikita Balesni, Marius Hobbhahn, David Lindner +13
We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through sc…
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…
The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks
Lucius Bushnaq, Stefan Heimersheim, Nicholas Goldowsky-Dill +7
Mechanistic interpretability aims to understand the behavior of neural networks by reverse-engineering their internal computations. However, current methods struggle to find clear…
Using Degeneracy in the Loss Landscape for Mechanistic Interpretability
Lucius Bushnaq, Jake Mendel, Stefan Heimersheim +5
Mechanistic Interpretability aims to reverse engineer the algorithms implemented by neural networks by studying their weights and activations. An obstacle to reverse engineering ne…
Localizing Model Behavior with Path Patching
Nicholas Goldowsky-Dill, Chris MacLeod, Lucas Sato +1
Localizing behaviors of neural networks to a subset of the network's components or a subset of interactions between components is a natural first step towards analyzing network mec…