Lee Sharkey

According to our database, Lee Sharkey authored at least 17 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Stochastic Parameter Decomposition.

Lucius Bushnaq, Dan Braun, Lee Sharkey

CoRR, June, 2025

Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video.

Sonia Joseph, Praneet Suresh, Lorenz Hufe, Edward Stevinson, Robert Graham, Yash Vadi, Danilo Bzdok, Sebastian Lapuschkin, Lee Sharkey, Blake Aaron Richards

CoRR, April, 2025

AI Behind Closed Doors: a Primer on The Governance of Internal Deployment.

Charlotte Stix, Matteo Pistillo, Girish Sastry, Marius Hobbhahn, Alejandro Ortega, Mikita Balesni, Annika Hallensleben, Nix Goldowsky-Dill, Lee Sharkey

CoRR, April, 2025

Identifying Sparsely Active Circuits Through Local Loss Landscape Decomposition.

Brianna Chrisman, Lucius Bushnaq, Lee Sharkey

CoRR, April, 2025

Open Problems in Mechanistic Interpretability.

Lee Sharkey, Bilal Chughtai, Joshua Batson, Jack Lindsey, Jeff Wu, Lucius Bushnaq, Nicholas Goldowsky-Dill, Stefan Heimersheim, Alejandro Ortega, Joseph Isaac Bloom, Stella Biderman, Adrià Garriga-Alonso, Arthur Conmy, Neel Nanda, Jessica Rumbelow, Martin Wattenberg, Nandi Schoots, Joseph Miller, Eric J. Michaud, Stephen Casper, Max Tegmark, William Saunders, David Bau, Eric Todd, Atticus Geiger, Mor Geva, Jesse Hoogland, Daniel Murfet, Tom McGrath

CoRR, January, 2025

Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition.

Dan Braun, Lucius Bushnaq, Stefan Heimersheim, Jake Mendel, Lee Sharkey

CoRR, January, 2025

Bilinear MLPs enable weight-based mechanistic interpretability.

Michael T. Pearce, Thomas Dooms, Alice Rigg, José Oramas, Lee Sharkey

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Sparse Autoencoders Do Not Find Canonical Units of Analysis.

Patrick Leask, Bart Bussmann, Michael T. Pearce, Joseph Isaac Bloom, Curt Tigges, Noura Al Moubayed, Lee Sharkey, Neel Nanda

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs.

Kola Ayonrinde, Michael T. Pearce, Lee Sharkey

CoRR, 2024

Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning.

Dan Braun, Jordan Taylor, Nicholas Goldowsky-Dill, Lee Sharkey

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Sparse Autoencoders Find Highly Interpretable Features in Language Models.

Robert Huben, Hoagy Cunningham, Logan Riggs Smith, Aidan Ewart, Lee Sharkey

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Black-Box Access is Insufficient for Rigorous AI Audits.

Stephen Casper, Carson Ezell, Charlotte Siegmann, Noam Kolt, Taylor Lynn Curtis, Benjamin Bucknall, Andreas A. Haupt, Kevin Wei, Jérémy Scheurer, Marius Hobbhahn, Lee Sharkey, Satyapriya Krishna, Marvin Von Hagen, Silas Alberti, Alan Chan, Qinyi Sun, Michael Gerovitch, David Bau, Max Tegmark, David Krueger, Dylan Hadfield-Menell

Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency, 2024

2023

A technical note on bilinear layers for interpretability.

Lee Sharkey

CoRR, 2023

2022

Circumventing interpretability: How to defeat mind-readers.

Lee Sharkey

CoRR, 2022

Interpreting Neural Networks through the Polytope Lens.

Sid Black, Lee Sharkey, Léo Grinsztajn, Eric Winsor, Dan Braun, Jacob Merizian, Kip Parker, Carlos Ramón Guevara, Beren Millidge, Gabriel Alfour, Connor Leahy

CoRR, 2022

Goal Misgeneralization in Deep Reinforcement Learning.

Lauro Langosco di Langosco, Jack Koch, Lee D. Sharkey, Jacob Pfau, David Krueger

Proceedings of the International Conference on Machine Learning, 2022

2021

Objective Robustness in Deep Reinforcement Learning.

Jack Koch, Lauro Langosco, Jacob Pfau, James Le, Lee Sharkey

CoRR, 2021