Sparse autoencoders on EEG transformers extract clinical features, identify three steering regimes, expose age-pathology entanglements and wrecking-ball failures, and map interventions to frequency spectra.
LEACE: Perfect linear concept erasure in closed form
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Probe-geometry alignment erases cross-sequence memorization signatures in LLMs below chance using per-depth rank-one activation interventions with negligible impact on zero-shot capabilities.
citing papers explorer
-
Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders
Sparse autoencoders on EEG transformers extract clinical features, identify three steering regimes, expose age-pathology entanglements and wrecking-ball failures, and map interventions to frequency spectra.
-
Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance
Probe-geometry alignment erases cross-sequence memorization signatures in LLMs below chance using per-depth rank-one activation interventions with negligible impact on zero-shot capabilities.