PRISMΔDB
SAE MODEL #2

FEATURE 2548

/ Feature 2548
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

Not interpreted yet.

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
0.00100
Peak Act
3.29
0.0 Max
Global Context
TOP ACTIVATING CONTEXTS
No cached examples found. Please scan the dataset.
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).