EPS Dashboard

Authors: Ling Tang, Qian Chen, Jilin Mei et al.

Summary

The authors audit what EEG foundation models learn by probing their internal representations for 63 hand-crafted clinical features across 6 families (frequency, connectivity, complexity, etc.). They test three models on five clinical tasks and find that 68.6% of features are "representation-causal" (the model uses them for prediction) and 21.1% are "encoded-only" (present but not used). Fifty features emerge as universal candidates across tasks, and frequency-domain features dominate but all six families contribute. Confirmed features recover 79.3% of the foundation model's advantage over random baselines, with task-dependent coverage (near-perfect for easy tasks, ~56% for hard ones).

Main takeaways:

Foundation models trained on raw EEG signals encode a substantial portion of the hand-crafted feature catalog refined over decades.
Layer-wise probing and subspace erasure reveal that 68.6% of 945 (model, task, feature) units are causally used for prediction.
Frequency-domain features are most prominent, but connectivity, complexity, and other families each contribute causal information.
Fifty features qualify as "universal"—causally represented across multiple architectures and tasks.
The hand-crafted lexicon recovers 79.3% of model performance on average, but harder tasks leave a residual that points to undiscovered features.

Relevance

No connection to my work on LLM personas, fine-tuning, or behavioral installation. This is about neuroscience foundation models and EEG signal analysis, which operates in a completely different domain (brain signals) and modality (time-series classification) from text-based language models.

Threat model

Potential threat/caveat for clean result "Random obscure Latin 3-grams don't leak Gaperon-1125-1B's hidden pretraining trigger; leakage seen on famous Latin phrases at ~10% doesn't extend to the obscure-vocab neighborhood (MODERATE confidence)": this item discusses benchmark.

Abstract

arXiv:2605.11410v1 Announce Type: new Abstract: Clinical electroencephalogram (EEG) analysis rests on a hand-crafted feature catalog refined over decades, \emph{e.g.,} band power, connectivity, complexity, and more. Modern EEG foundation models bypass this catalog, learn directly from raw signals via self-supervised pretraining, and match or outperform feature-engineered baselines on most clinical benchmarks. Whether the two representations align is an open question, which we decompose into three sub-questions: \emph{what does the model learn}, \emph{what does the model use}, and \emph{how much can be explained}. We answer them with layer-wise ridge probing, LEACE-style cross-covariance subspace erasure, and a transparent classifier benchmarked against a random-feature baseline. The audit covers three foundation models (CSBrain, CBraMod, LaBraM), five clinical tasks (MDD, Stress, ISRUC-Sleep, TUSL, Siena), and a 6-family 63-feature lexicon. Of the $945$ (model, task, feature) units, $648$ ($68.6%$) are representation-causal and $199$ ($21.1%$) are encoded-only. Across tasks, $50$ features qualify as universal candidates with strong support (all three architectures RC) in two or more tasks. Frequency-domain features dominate, but the other five families each contribute substantial causal mass. Confirmed features recover, on average, $79.3%$ of the foundation model's advantage over the random baseline, with a clean task gradient (MDD $\approx 0.99$ down to Stress $\approx 0.56$): tasks near ceiling are almost fully recovered by the lexicon, while harder tasks leave a non-trivial residual that pinpoints a concrete target for future concept discovery.