144,000 probing evals show Act@100 and LN2@60 beat last-layer probing in transformers

CatAstro_Piyush · x · 2026-11-17

A new paper from Noah's Ark Lab, EPFL and collaborators runs 144,000+ linear probing evaluations across vision foundation models and LLMs to answer which transformer representation to probe.

Key findings:

Paper, code and HuggingFace resources are public.

Original post →

More from Research

Research channel →