community
active
leiden_hybrid_concepts
label: sonnet
community:leiden_hybrid_concepts-run2-c70SAE Feature Geometry in Biomedical Signals
Evaluating sparse autoencoder monosemanticity and entanglement using clinical taxonomy grounding across EEG/sleep foundation models.
3 members. Each node is clickable.
Loading graph…
Drawn from 2 sources
The papers/notes whose extracted claims & findings make up this cluster.
Bridges (2)
Other communities that share members with this one — cross-cutting threads or papers that sit at the seam between two themes.
Claims (2)
- SAE features can be grounded in clinical taxonomy (abnormality, age, sex, medication) to benchmark monosemanticity and entanglement.Claim that feature grounding enables interpretability metrics.
- SAE features tend to shatter manifolds into many small and apparently-unrelated pieces, obscuring the overarching semantic structure.Core critique of sparse autoencoders: they break the geometric structure of representations, making it harder to see the big picture.
Findings (1)
- Monosemanticity and entanglement of SAE features were benchmarked for clinical taxonomy grounding across SleepFM, REVE, LaBraM.Quantitative assessment of feature quality using clinical concepts across models.