Safety researcher
Catherine Olsson
Co-discovered induction heads, a concrete mechanism explaining how Transformers perform in-context learning.
Works in the archive (3) · lead author on 1
- A Mathematical Framework for Transformer Circuits · 2021
- LeadIn-context Learning and Induction Heads · 2022
- Toy Models of Superposition · 2022
“Lead” marks the first-listed author — a byline fact, not a measure of influence; co-authorship is shown as recorded.
Co-authors in the archive
View co-author network (7 people)
Loading graph…