PRISMΔDB
SAE MODEL #2

FEATURE 2972

/ Sensory-Motor Integration
Refresh Stats

This page shows the detailed analysis of a specific feature in the Sparse Autoencoder (SAE). It includes the semantic interpretation generated by the LLM, the top activating documents that trigger this feature, and statistical metrics like density and activation distribution.

Semantic Interpretation
gemma3:12b #15

The neuron appears to activate when there's a connection or interaction between sensory input (visual, tactile, auditory) and motor actions (pointing, saccades, detection). It's involved in how the brain processes and integrates sensory information to guide behavior, particularly when there's a need to filter or prioritize sensory cues. The examples involve tactile cues influencing visual attention, spoken words affecting visual perception, and the relationship between perception and motor actions in individuals with brain lesions. The concept isn't simply about sensory processing or motor control, but the *integration* of the two.

STATISTICS & DISTRIBUTION
Statistics Explained

Density
Fraction of documents where this feature activates at least once.
Higher density = feature appears frequently across the dataset.

Peak Activation
Maximum activation value observed for this feature over all documents.

Activation Histogram
Distribution of all activation values for this feature. Each bar represents a bin (range) of values, and its height shows how many documents fall in that range.

Density
0.02700
Peak Act
3.66
0.0 Max
Global Context
TOP ACTIVATING CONTEXTS
DOC #64 ANALYZE
ACT: 3.6602
Acute Stimulant Treatment and Reinforcement Increase the Speed of Information Accumulation in Children with ADHD. The current studies utilized drift diffusion modeling (DDM) to examine how reinforcement and stimulant medication affect cognitive task performance in children with ADHD. In Study 1, children with (n = 25; 88 % male) and without ADHD (…
DOC #267 ANALYZE
ACT: 3.2979
Directing visual attention with spatially informative and spatially noninformative tactile cues. We investigated the tactile cuing of visual spatial attention using spatially-informative (75% valid) and spatially-noninformative (25% valid) tactile cues. The participants performed a visual change detection task following the presentation of a tacti…
DOC #78 ANALYZE
ACT: 3.1309
Implicit semantic perception in object substitution masking. Decades of research on visual perception has uncovered many phenomena, such as binocular rivalry, backward masking, and the attentional blink, that reflect 'failures of consciousness'. Although stimuli do not reach awareness in these paradigms, there is evidence that they nevertheless un…
DOC #822 ANALYZE
ACT: 2.9128
Spatial perception errors do not predict pointing errors by individuals with brain lesions. We examined the relationship between errors in sensorimotor transformations (SMT) for reaching to external targets and visual and kinesthetic spatial perception of those targets by participants with damage to the posterior parietal lobule (PPL) and adjacent…
DOC #318 ANALYZE
ACT: 2.7377
Spoken words can make the invisible visible-Testing the involvement of low-level visual representations in spoken word processing. The notion that processing spoken (object) words involves activation of category-specific representations in visual cortex is a key prediction of modality-specific theories of representation that contrasts with theorie…
DOC #77 ANALYZE
ACT: 2.7185
Shared and Subject-Specific Dictionary Learning (ShSSDL) Algorithm for Multisubject fMRI Data Analysis. Analysis of functional magnetic resonance imaging (fMRI) data from multiple subjects is at the heart of many medical imaging studies, and approaches based on dictionary learning (DL) are recently noted as promising solutions to the problem. Howe…
TOPOLOGY
CORRELATIONS
W – Weight-space · similarity between decoder vectors (features that point in similar directions in the embedding space).
D – Data / co-activation · features that tend to fire together on the same documents (co-occurrence in the dataset).