ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2209.11895
203
326

In-context Learning and Induction Heads

24 September 2022
Catherine Olsson
Nelson Elhage
Neel Nanda
Nicholas Joseph
Nova Dassarma
T. Henighan
Benjamin Mann
Amanda Askell
Yuntao Bai
Anna Chen
Tom Conerly
Dawn Drain
Deep Ganguli
Zac Hatfield-Dodds
Danny Hernandez
Scott Johnston
Andy Jones
John Kernion
Liane Lovitt
Kamal Ndousse
Dario Amodei
Tom B. Brown
Jack Clark
Jared Kaplan
Sam McCandlish
C. Olah
ArXivPDFHTML
Abstract

"Induction heads" are attention heads that implement a simple algorithm to complete token sequences like [A][B] ... [A] -> [B]. In this work, we present preliminary and indirect evidence for a hypothesis that induction heads might constitute the mechanism for the majority of all "in-context learning" in large transformer models (i.e. decreasing loss at increasing token indices). We find that induction heads develop at precisely the same point as a sudden sharp increase in in-context learning ability, visible as a bump in the training loss. We present six complementary lines of evidence, arguing that induction heads may be the mechanistic source of general in-context learning in transformer models of any size. For small attention-only models, we present strong, causal evidence; for larger models with MLPs, we present correlational evidence.

View on arXiv
Comments on this paper