Probing Transformer Representations Layer by Layer, Module by Module

Ambroise Odonnat, Theo Gnassounou, Laetitia Chapel, Romain Tavenard, Ievgen Redko

Probing Transformer Representations Layer by Layer, Module by Module: 0 upvotes on Hugging Face Daily Papers, #20 of 21 papers on 2026-11-12. Day-by-day upvote history.

Upvotes over time

It had 0 upvotes by its first day, 0 upvotes by the next day, 0 upvotes by day 3, 0 upvotes by day 7, and has 0 now. It ranked #132 of 133 papers in its week and #336 of 340 in its month. Its code repository has 1 GitHub stars.

Which representation should be probed in a transformer-based foundation model? Recent work shows that the standard practice of probing the final layer is often suboptimal, as intermediate layers can provide better features. Yet, representations are still largely studied along depth alone, treating each transformer block as an atomic unit. In this work, we analyze transformer representations layer by layer, module by module. Through more than 144,000 linear probing evaluations of vision foundation models (VFMs) and large language models (LLMs), we show that layer and module choices should be considered jointly: the best layer-module pair yields substantially larger gains over the final-layer residual stream than the best layer with the residual stream fixed. Moreover, module performance can vary substantially across layers, showing that useful representations cannot be characterized by depth alone. Building on these findings, we evaluate simple fixed probing strategies: the final-layer feedforward activation (Act@100) for vision and the second normalization layer at 60% depth (LN2@60) for language. These strategies improve over the probing baseline in a majority of evaluations and recover, on average, 42% and 86% of the gains from probing the best layer-module pair for vision and language, respectively. For VFMs, these gains increase with the transfer difficulty between pretraining and downstream data.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.