Resources: Interpretability 9

Resources (3 hrs 40 mins)

• Toy models of superposition

  Nelson Elhage, Tristan Hume and Catherine Olsson et al. · 2022 · 45 min ·

  Listen to article

  Create a free account to track your progress and unlock access to the full course content.

• Discovering Latent Knowledge in Language Models Without Supervision

  Collin Burns, Haotian Ye and Dan Klein et al. · 2022 · 30 min ·

  Listen to article

  Create a free account to track your progress and unlock access to the full course content.

• A mechanistic interpretability analysis of grokking

  Neel Nanda, Lawrence Chan and Tom Lieberum et al. · 2022 · 35 min

  Create a free account to track your progress and unlock access to the full course content.

• Polysemanticity and capacity in neural networks

  Adam Scherlis, Kshitij Sachan and Adam S. Jermyn et al. · 2022 · 35 min

  Create a free account to track your progress and unlock access to the full course content.

• Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small

  Kevin Wang, Alexandre Variengien and Arthur Conmy et al. · 2023 · 35 min ·

  Listen to article

  Create a free account to track your progress and unlock access to the full course content.

• ROME: Locating and Editing Factual Associations in GPT

  Kevin Meng, David Bau and Alex Andonian et al. · 2022 · 35 min

  Create a free account to track your progress and unlock access to the full course content.