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

#gemma-2

0 stories this week · 1 this month · 1 in 6 months · mostly AI

Stories per day · 30 days

Relateddata-efficiency1 feature-reproducibility1 interpretability1 mechanistic-interpretability1 sparse-autoencoders1

1 stories, newest first · one card per story

Hugging Face daily papers12d ago

Diminishing Returns of Data in Sparse Autoencoders: Functional Behavior does not Guarantee Feature Reproducibility

SAE reconstruction converges on far less data, but one-to-one feature matches keep rising with more tokens.

sparse-autoencoders interpretability

1