Interpretability finding: top circuit components don't fully explain model predictions
Sauers_ · x · 2026-10-02
The author cites interpretability research arguing that the top network components "do not provide anything close to a full account of the relevant computation" behind a model's prediction. The quoted example: a base model predicts "her" after "The princess lost..." via two separate computational pathways — the femaleness of the princess token plus grammatical pronoun prediction after verbs — showing limits of attributing behavior to single components.
More from Research
- LEV: Looped decision model lifts 2.6B accuracy 63.2% to 76.2% with adaptive compute — jiqizhixin · 2026-11-19
- Aurora2-400M-A20M: a sparse MoE pretrained from scratch in 36 hours on one RTX Pro 6000 — Tall_Abrocoma_3533 · 2026-11-19
- Researcher calls METR/Anthropic '2x speedup' RSI analysis statistically dubious — jessi_cata · 2026-11-19
- Linear Probes Could Reveal Which Persona a Base Model Is Playing, Researchers Suggest — cephaloform · 2026-11-19
- ETH's Anymal robot completes 10km autonomous alpine hike with VLM-guided ROAM system — ChongZzZhang · 2026-11-19
- OpenVax codebase grows from 78K to 565K lines in 15 months — iskander · 2026-11-19