Causal scrubbing: Appendix — LessWrong

* Authors sorted alphabetically. • An appendix to this post. • 1 More on Hypotheses …

x Causal scrubbing: Appendix — LessWrong [Redwood Research] Causal Scrubbing Causal Scrubbing Interpretability (ML & AI) Redwood Research AI Frontpage 18 Causal scrubbing: Appendix by LawrenceC , Adrià Garriga-alonso , Nicholas Goldowsky-Dill , ryan_greenblatt , jenny , Ansh Radhakrishnan , Buck , Nate Thomas 3rd Dec 2022 AI Alignment Forum 24 min read 4 18 Ω 11 * Authors sorted alphabetically. An appendix to this post . 1 More on Hypotheses 1.1 Example behaviors As mentioned above, our method allows us to explain quantitatively measured model behavior operationalized as the expectation of a f

saved by

• Danish

related reading

• Causal Scrubbing: a method for rigorously testing interpretability hypotheses [Redwood Research] — LessWronglesswrong.com
• Faithful, Interpretable Model Explanations via Causal Abstraction | SAIL Blogai.stanford.edu
• An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
• Attribution Patching: Activation Patching At Industrial Scale - Neel Nandaneelnanda.io
• Weight-Sparse Circuits May Be Interpretable Yet Unfaithful — LessWronglesswrong.com
• An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
• A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org
• Interpretability Dreamstransformer-circuits.pub
• Do reasoning models use their scratchpad like we do? Evidence from distilling paraphrasesalignment.anthropic.com
• Neel Nanda on Mechanistic Interpretability: Progress, Limits, and Paths to Safer AI — EA Forumforum.effectivealtruism.org
• Thought Branches: Interpreting LLM Reasoning Requires Resamplingarxiv.org
• ARC progress update: Competing with sampling — LessWronglesswrong.com