Residual-stream interpretation method beats k-means for tag clustering
amplifiedamp · x · 2026-10-20
- Method: amplifiedamp applied a residual-stream interpretation technique (developed by friends) to a base model's residual stream, producing more useful clusters of tags than k-means clustering over the last layer.
- Output: Built a dendrogram and a search engine from the clusters.
- Caveat: The dataset (EAG NYC attendees) is boring and not shareable, so the search engine can't be released publicly.
Related event: Residual Stream Interpretation Method Beats Last-Layer k-means Clustering(2 posts)→
More from Research
- RFD4-Proteina's 'underrated' docs detail partial diffusion for protein redesign — AllThingsApx · 2026-10-23
- MPI-Sec PhD Thesis on Vulnerability Detection Benchmarks Includes Pre-LLM Classic "Top Score on the Wrong Exam" — mboehme_ · 2026-10-23
- LiveNerf's 29-day data finds no nerfing of Claude Opus 5.5 — TheOnlyVibemaster · 2026-10-23
- New paper makes 9 falsifiable predictions toward a major AI-enabled terror attack by 2027-2028 — StephenLCasper · 2026-10-23
- HumanoidPose recovers humanoid robots' full-body joint states from RGB video alone — cholz · 2026-10-23
- Sophont's Holon-S1 predicts genes and biomarkers from routine pathology slides — iScienceLuvr · 2026-10-23