finding
active
finding:spectral-decoder-maps-concept-interventions-to-pathological-slow-wave-suppression-and-alpha-band-restorationSpectral decoder maps concept interventions to pathological slow-wave suppression and alpha-band restoration.
Physiological interpretability result linking latent steering to EEG frequency signatures.
Source paper
extracted_from(2026) · William Lehn-Schiøler · Magnus Ruud Kjær · Rahul Thapa · M. Pedersen +9
Neighborhood — ranked by edge-count
Claims (1)
claim
- Claim that the spectral decoder adds physiological interpretability.
Communities (3)
community
- Spans attention head decomposition, benchmark awareness, and genomic pathogenicity prediction via neural models.
- Tracing information flow through weight matrices and attention heads using attribution graphs to identify causally important subcomponents in language models.
- Maps concept-based neural interventions to frequency-domain biomarkers, enabling physiologically interpretable EEG/neural signatures.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Links latent space manipulation to known EEG neurophysiology
- Key result linking abstract latent manipulations to known EEG neurophysiology
- Links latent space manipulation to known EEG neurophysiology
- EEG frequency signature of reduced slow-wave activity, obtained as a spectral interpretation of steering.
- Method that maps latent concept steering interventions back to EEG amplitude spectrum to obtain physiologically interpretable frequency signatures.
- Key quote connecting path redundancy to interferometric information encoding.
- Argues that intervening control layers decompose the genotype-phenotype mapping into two easier problems.
- Implicit predictive hypothesis from the cancer-as-cognitive-defect claim, with experimental implications for regenerative medicine