abnormality

EEG abnormality concept (e.g., epileptiform activity) used to interpret SAE features.

Neighborhood — ranked by edge-count

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 Abnormalityconcept0.823
One of four clinical taxonomy dimensions used to benchmark SAE features
Clinical Taxonomy: abnormality, age, sex, medicationconcept0.761
Set of clinical concepts used as a grounding vocabulary to benchmark SAE feature monosemanticity and entanglement.
linearityconcept0.757
The sequential, continuous order of text, often challenged by diagrammatic branching.
Individualityconcept0.757
Formal notion of what constitutes an individual agent; bridges Buddhist and information-theoretic perspectives.
intentionalityconcept0.743
The capacity to have beliefs, desires, intentions; discussed in the context of AI and speech acts.
Biological Individualityconcept0.736
Central concept challenged in paper; traditionally defined by genetic identity or evolutionary units but shown to be more about cognitive organization and information integration.
Organismic Individualityconcept0.733
Property where development and behavior of whole is non-decomposable function of component parts; distinct from genetic individuality.
Nonlinearityconcept0.730