EEG foundation models

Large transformer models pretrained on EEG data for clinical tasks; the object of interpretability in this paper.

Neighborhood — ranked by edge-count

framework

LaBraM
associated_with
EEG transformer foundation model for brain activity analysis, one of the three architectures studied.
REVE
associated_with
EEG transformer foundation model (representation model) analyzed in the study.
SleepFM
associated_with
EEG transformer foundation model for sleep staging, one of the three analyzed architectures.

event

Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders (2026)
mentions
Preprint applying TopK SAEs to three EEG transformers to reveal sparse feature dictionaries, steering regimes, and spectral interpretation.

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

EEG foundation models achieve state-of-the-art clinical performance yet their internal computations remain opaque, constituting a barrier to clinical trust.claim0.830
Motivating claim for the entire paper
Foundation Modelsconcept0.806
Large pretrained models used as backbones across tasks; their universality motivates the convergence hypothesis
How are clinical concepts represented and steerable in EEG foundation models?question0.804
Core research question driving the mechanistic investigation.
Clinical concepts in EEG foundation models fall into three operational regimes: selectively steerable, encoded but entangled, and non-encoded.claim0.783
Interpretive claim summarizing the spectrum of concept steerability discovered.
What clinical concepts are encoded in the internal representations of EEG foundation models?question0.780
Primary research question driving the extraction and benchmarking of SAE features
Genomic Foundation Modelsconcept0.776
Large pretrained models for genomic sequences; subject of this work's pooling improvements.
EEG Transformer Embeddingsconcept0.745
The internal representations of EEG transformers from which SAE features are extracted
What physiologically interpretable frequency signatures correspond to latent concept steering manipulations in EEG foundation models?question0.740
Research question motivating the spectral decoder methodology