3 citations · 3 across the 4 of their papers we have counts for
4 papers
Evaluating and Designing Sparse Autoencoders by Approximating Quasi-Orthogonality
Sewoong Lee, Adam Davies, Marc E. Canby +1
Sparse autoencoders (SAEs) are widely used in mechanistic interpretability research for large language models; however, the state-of-the-art method of using -sparse autoencoders…
Social Science Is Necessary for Operationalizing Socially Responsible Foundation Models
Adam Davies, Elisa Nguyen, Michael Simeone +2
With the rise of foundation models, there is growing concern about their potential social impacts. Social science has a long history of studying the social impacts of transformativ…
The Cognitive Revolution in Interpretability: From Explaining Behavior to Interpreting Representations and Algorithms
Adam Davies, Ashkan Khakzar
Artificial neural networks have long been understood as "black boxes": though we know their computation graphs and learned parameters, the knowledge encoded by these weights and fu…
How Reliable are Causal Probing Interventions?
Marc Canby, Adam Davies, Chirag Rastogi +1
Causal probing aims to analyze foundation models by examining how intervening on their representation of various latent properties impacts their outputs. Recent works have cast dou…