Selected papers

See my Google Scholar for a full list of publications.

1. Using OCR Heads to Verbalize Image Semantics

   
   Sheridan Feucht, Benno Krojer, Sarah Wang, Henry Abrahamsen, Byron Wallace, David Bau
   Preprint, 2026.

2. Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts

   
   Sheridan Feucht*, Tal Haklay*, Usha Bhalla, Daniel Wurgaft, Can Rager, Raphaël Sarfati, Jack Merullo, Thomas McGrath, Owen Lewis, Ekdeep Singh Lubana*, Thomas Fel*, Atticus Geiger*
   Third Conference on Language Modeling (COLM), 2026.

3. The Dual-Route Model of Induction

   
   Sheridan Feucht, Eric Todd, Byron Wallace, David Bau
   Second Conference on Language Modeling (COLM), 2025.

4. Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs

   
   Sheridan Feucht, David Atkinson, Byron Wallace, David Bau
   Empirical Methods in Natural Language Processing (EMNLP), 2024.

click me to see a hand-picked track for each paper 🎧

Other Works

1. Vector Arithmetic in Concept and Token Subspaces

   
   Sheridan Feucht, Byron Wallace, David Bau
   Mechanistic Interpretability Workshop at NeurIPS, 2025.

2. Does FLUX Know What It's Writing?

   
   Adrian Chang*, Sheridan Feucht*, Byron Wallace, David Bau
   Mechanistic Interpretability Workshop at NeurIPS, 2025.

3. In-Context Learning Without Copying

   
   Kerem Sahin, Sheridan Feucht, Adam Belfki, Jannik Brinkmann, Aaron Mueller, David Bau, Chris Wendler
   Preprint (November 2025).

4. Erasing Conceptual Knowledge from Language Models

   
   Rohit Gandikota, Sheridan Feucht, Samuel Marks, David Bau
   Conference on Neural Information Processing Systems (NeurIPS), 2025.

5. Deep Neural Networks Can Learn Generalizable Same-Different Visual Relations

   
   Alexa R. Tartaglini*, Sheridan Feucht*, Michael A. Lepori, Wai Keen Vong, Charles Lovering, Brenden M. Lake, Ellie Pavlick
   Conference on Cognitive Computational Neuroscience, 2025.