saprmarks: Supervised Activation Probes Aren't Mechanistic Interpretability Either
saprmarks · x · 2026-09-07
In the same thread, saprmarks adds that he does not view supervised activation probes as mechanistic interpretability methods either, for similar reasons as his earlier claim about activation oracles and NLAs.
More from Research
- Study: GPT-4 finds abusing a man to prevent nuclear apocalypse more acceptable than abusing a woman — pmddomingos · 2026-10-24
- Jon Barron: every softmax & cross-entropy implementation (JAX, PyTorch) has two subtle bugs — code_star · 2026-10-24
- Fudan's F2G-Pose estimates 6D pose, size and shape from one RGB-D image at 28 FPS — joemeno · 2026-10-24
- All 100 blockbuster drugs mapped onto 3D target structures with mechanism explainers — CatAstro_Piyush · 2026-10-24
- Steering vector arithmetic: catdog + soldier = military dog, and model identity confusion — voooooogel · 2026-10-24
- Dev squeezes a 7M-param byte-level LLM entirely into an RTX 4090's on-chip memory — dejanseo · 2026-10-24