NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#linear-representation-hypothesis

0 stories this week · 0 this month · 2 in 6 months · mostly AI

Stories per day · 30 days

2 stories, newest first · one card per story

Hugging Face daily papersSep 21, 2026

The Linear Representation Hypothesis Needs a Group Action

Researchers argue the Linear Representation Hypothesis is a family of claims distinguished by group-action equivalence.

interpretability linear-representation-hypothesis

1

arXiv cs.AI / cs.LG / cs.CLSep 17, 2026

Local Sparsity Enables Unsupervised LLM Safety Detection

Proposes locally masked sparse-autoencoder anomaly detection that flags unsafe LLM outputs unsupervised, using only 1-2% of SAE neurons.

activation-analysis anomaly-detection

1