Stefan Heimersheim

According to our database, Stefan Heimersheim authored at least 11 papers between 2023 and 2025.

Collaborative distances:

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

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

2024

Investigating Sensitive Directions in GPT-2: An Improved Baseline and Comparative Analysis of SAEs.

Daniel J. Lee, Stefan Heimersheim

CoRR, 2024

Evolution of SAE Features Across Layers in LLMs.

Daniel Balcells, Benjamin Lerner, Michael Oesterle, Ediz Ucar, Stefan Heimersheim

CoRR, 2024

Characterizing stable regions in the residual stream of LLMs.

Jett Janiak, Jacek Karwowski, Chatrik Singh Mangat, Giorgi Giglemiani, Nora Petrova, Stefan Heimersheim

CoRR, 2024

Evaluating Synthetic Activations composed of SAE Latents in GPT-2.

Giorgi Giglemiani, Nora Petrova, Chatrik Singh Mangat, Jett Janiak, Stefan Heimersheim

CoRR, 2024

You can remove GPT2's LayerNorm by fine-tuning.

Stefan Heimersheim

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

How to use and interpret activation patching.

Stefan Heimersheim, Neel Nanda

CoRR, 2024

2023

Towards Automated Circuit Discovery for Mechanistic Interpretability.

Arthur Conmy, Augustine N. Mavor-Parker, Aengus Lynch, Stefan Heimersheim, Adrià Garriga-Alonso

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023