Tagged: Safety

Articles

• Fundamentals · Part 16How LLMs Work

  Inside the Black Box: Features, Superposition and Circuits

  How researchers read an LLM's internals: the logit lens, superposition, sparse autoencoders, circuits and steering, with real numbers and honest limits.

• Interpretability · Part 1Interpretability

  Opening the Black Box: What Interpretability Can Explain

  What interpretability is for, its main methods, what counts as an explanation, and the toolkit, tested by asking two methods where GPT-2 keeps facts.

• Interpretability · Part 9Interpretability

  Steering With Activations: The Refusal Direction, Measured

  Find one direction that controls refusal in an open chat model, remove it and add it, measure the side effects, and compare SAE steering with a mean difference.

• Interpretability · Part 11Interpretability

  Interpretability for Safety: Lie Detectors, Sycophancy and Audits

  What looking inside a model can and can't check about its honesty: lie and sycophancy probes, model diffing and real audits, measured on Gemma 2 2B.

• Interpretability · Part 12Interpretability

  Limits and Open Problems in Interpretability

  The series in review: every part's headline result, a robustness audit of three of them, the field's sharpest critiques, and the problems still open.