Stefan Heimersheim

Publication Activity (10 Years)

Years Active: 2023-2024
Publications (10 Years): 5

Top Topics

Data Corruption

Prediction Accuracy

Analog Circuits

Top Venues

Publications

Stefan Heimersheim, Neel Nanda
How to use and interpret activation patching. CoRR (2024)
Lucius Bushnaq, Stefan Heimersheim, Nicholas Goldowsky-Dill, Dan Braun, Jake Mendel, Kaarel Hänni, Avery Griffin, Jörn Stöhler, Magdalena Wache, Marius Hobbhahn
The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks. CoRR (2024)
Lucius Bushnaq, Jake Mendel, Stefan Heimersheim, Dan Braun, Nicholas Goldowsky-Dill, Kaarel Hänni, Cindy Wu, Marius Hobbhahn
Using Degeneracy in the Loss Landscape for Mechanistic Interpretability. CoRR (2024)
Arthur Conmy, Augustine N. Mavor-Parker, Aengus Lynch, Stefan Heimersheim, Adrià Garriga-Alonso
Towards Automated Circuit Discovery for Mechanistic Interpretability. CoRR (2023)
Arthur Conmy, Augustine N. Mavor-Parker, Aengus Lynch, Stefan Heimersheim, Adrià Garriga-Alonso
Towards Automated Circuit Discovery for Mechanistic Interpretability. NeurIPS (2023)