claim

active

claim:spectral-decoding-of-concept-interventions-can-provide-physiologically-interpretable-frequency-signatures

Spectral decoding of concept interventions can provide physiologically interpretable frequency signatures.

Claim that the spectral decoder adds physiological interpretability.

Source paper

extracted_from

Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders

(2026) · William Lehn-Schiøler · Magnus Ruud Kjær · Rahul Thapa · M. Pedersen +9

Neighborhood — ranked by edge-count

Findings (1)

finding

Spectral decoder maps concept interventions to pathological slow-wave suppression and alpha-band restoration.
supports
Physiological interpretability result linking latent steering to EEG frequency signatures.

Communities (3)

community

Mechanistic interpretability & model evaluation
members_of
Spans attention head decomposition, benchmark awareness, and genomic pathogenicity prediction via neural models.
Mechanistic interpretability via parameter decomposition
members_of
Tracing information flow through weight matrices and attention heads using attribution graphs to identify causally important subcomponents in language models.
Spectral decoding of neural interventions
members_of
Maps concept-based neural interventions to frequency-domain biomarkers, enabling physiologically interpretable EEG/neural signatures.

Related by similarity (8)

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.

Spectral decoder reveals α-band restoration as a frequency signature of concept steering interventions in EEG foundation models.finding0.855
Links latent space manipulation to known EEG neurophysiology
Spectral decoder reveals pathological slow-wave suppression as a frequency signature of concept steering interventions in EEG foundation models.finding0.845
Links latent space manipulation to known EEG neurophysiology
The spectral decoder successfully translates latent SAE interventions into physiologically interpretable frequency signatures such as slow-wave suppression and α-band restoration.claim0.844
Key result linking abstract latent manipulations to known EEG neurophysiology
What physiologically interpretable frequency signatures correspond to latent concept steering manipulations in EEG foundation models?question0.826
Research question motivating the spectral decoder methodology
S suggests practical diagnostics for prompt design, retrieval, and light fine-tuning without additional training infrastructure.claim0.758
Applied contribution.
The same charitable interpretation must be extended to all systems that display observable response patterns that are consistent with animal cognition, including artificial intelligences, metaplastic materials, and robotic systems.claim0.745
Call to extend the inference of sentience to non-biological systems as well.
The likelihood of a dedicated feature for a concept (element, city, animal, food) follows a sigmoid in log-frequency of the concept in training data, with threshold frequency inversely proportional to number of alive features.finding0.745
Quantitative relationship between concept frequency and feature presence.
Lindsey 2025: frontier models can detect and report changes in their own internal activations via concept injection experiments, demonstrating functional introspective awarenessfinding0.738
Prior finding cited as convergent evidence for LLM self-awareness capacities