trends.barnas.net

method · first seen 6 Oct 2026

representation probing

Also: probing, probing classifiers, concept-based model monitoring, probing of internal representations, linear probing of vision-language model layers, linear probing of self-supervised speech models

Training simple classifiers on frozen model activations to test what information a network encodes internally.

Mentions per week

0519 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Rank 88 on 16 Nov 2026 · 7 mentions in 28 days · 7 independent groups · papers · first seen 6 weeks ago · acceleration +1.90

Earliest sources

Latest sources

Mentioned together with

vision-language modelvariational autoencoderRAVEsocial attributionactivation steeringinverse reinforcement learningretrieval-augmented generationlatent reasoningsparse autoencoderlatent multi-hop reasoning