Nicholas Goldowsky-Dill

According to our database, Nicholas Goldowsky-Dill authored at least 9 papers between 2023 and 2025.

Collaborative distances:

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

2025

Stress Testing Deliberative Alignment for Anti-Scheming Training.

Bronson Schoen, Evgenia Nitishinskaya, Mikita Balesni, Axel Højmark, Felix Hofstätter, Jérémy Scheurer, Alexander Meinke, Jason Wolfe, Teun van der Weij, Alex Lloyd, Nicholas Goldowsky-Dill, Angela Fan, Andrei Matveiakin, Rusheb Shah, Marcus Williams, Amelia Glaese, Boaz Barak, Wojciech Zaremba, Marius Hobbhahn

CoRR, September, 2025

Detecting Strategic Deception Using Linear Probes.

Nicholas Goldowsky-Dill, Bilal Chughtai, Stefan Heimersheim, Marius Hobbhahn

CoRR, February, 2025

Open Problems in Mechanistic Interpretability.

Lee Sharkey, Bilal Chughtai, Joshua Batson, Jack Lindsey, Jeffrey 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, William Saunders, Eric J. Michaud, Stephen Casper, Max Tegmark, David Bau, Eric Todd, Atticus Geiger, Mor Geva, Jesse Hoogland, Daniel Murfet, Tom McGrath

Trans. Mach. Learn. Res., 2025

Detecting Strategic Deception with Linear Probes.

Nicholas Goldowsky-Dill, Bilal Chughtai, Stefan Heimersheim, Marius Hobbhahn

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

Towards evaluations-based safety cases for AI scheming.

Mikita Balesni, Marius Hobbhahn, David Lindner, Alexander Meinke, Tomek Korbak, Joshua Clymer, Buck Shlegeris, Jérémy Scheurer, Charlotte Stix, Rusheb Shah, Nicholas Goldowsky-Dill, Dan Braun, Bilal Chughtai, Owain Evans, Daniel Kokotajlo, Lucius Bushnaq

CoRR, 2024

The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks.

Lucius Bushnaq, Stefan Heimersheim, Nicholas Goldowsky-Dill, Dan Braun, Jake Mendel, Kaarel Hänni, Avery Griffin, Jörn Stöhler, Magdalena Wache, Marius Hobbhahn

CoRR, 2024

Using Degeneracy in the Loss Landscape for Mechanistic Interpretability.

Lucius Bushnaq, Jake Mendel, Stefan Heimersheim, Dan Braun, Nicholas Goldowsky-Dill, Kaarel Hänni, Cindy Wu, Marius Hobbhahn

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

2023

Localizing Model Behavior with Path Patching.

Nicholas Goldowsky-Dill, Chris MacLeod, Lucas Sato, Aryaman Arora

CoRR, 2023