• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small.

Kevin WangAlexandre VariengienArthur ConmyBuck ShlegerisJacob Steinhardt
Published in: CoRR (2022)
Keyphrases
  • object identification
  • image matching
  • object recognition
  • computer vision
  • object views
  • feature space
  • markov random field