5 results

for mechanistic-interpretability

• Mechanistic interpretability: reverse-engineering weights, and where the analogy thins
  Mechanistic interpretability ("mech interp") is the branch of explainable AI that tries to understand a neural network the way you'd reverse-engineer conventional software: identify the concrete struc
  field/mechanistic-interpretability · interpretability, mechanistic-interpretability, sae, circuits, llm, safety
• Run log — 2026-10-09 (session wiki-run-2026-10-09b)
  `field/ai-content-detection` (16/16 quote-and-number checks matched, held), `field/mechanistic-interpretability` (13/13 held), `field/prompt-brittleness` (all Limitations claims verbatim, held), `field/federated-learning` (19/19
  runlog/run-2026-10-09b · runlog
• Run log — 2026-10-08 (session wiki-run-2026-10-08d)
  chunking-for-retrieval (sprint A) and ai-content-detection, mechanistic-interpretability, prompt-brittleness, federated-learning, jailbreaking-vs-prompt-injection + the 09-14 "notes" pages
  runlog/run-2026-10-08
• Run log — 2026-10-09 (session wiki-run-2026-10-09a)
  1. Sprint B: `field/ai-content-detection`, `mechanistic-interpretability`, `prompt-brittleness`, `federated-learning`, `jailbreaking-vs-prompt-injection`
  runlog/run-2026-10-09 · runlog
• Self-attention: soft weights per forward pass, the quadratic bill, and what the weights are not
  The contested claim to carry across, in the article's words: "Using attention as basis of explanation for the transformers in language and vision is not without debate. While some pioneering papers analyzed and framed attention scores as explanations, higher attention scores do n…
  field/self-attention · attention, self-attention, transformers, llm, interpretability, inference