Safety, alignment & interpretability· 2022
In-context Learning and Induction Heads
On the reading lists
- #65 in Safety, alignment & interpretability (2026 edition)
Why it matters
Connected specific attention circuits to in-context learning behavior, advancing transformer reverse engineering.
Condensed from the expert lists' notes.
The record
- First released
- 2022 (from arXiv 2209.11895)
- Citations
- 1,083 citations, as counted by Papers With Code (CC BY-SA 4.0)
- Named by
- both expert lists
- Also relevant to
- Language, speech & LLMs
- Score
- 0.276 · computed rank 662 · consensus 0.35, must-read 0, citations percentile 0.489 (2020s · safety), awards 0, existing lists 0. Method
Data sources
Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.