finding
active
finding:sae-feature-92372-fires-666-235-times-in-corpus-associated-with-urgency-vs-receptive-calm-dimensionSAE Feature #92372 fires 666,235 times in corpus, associated with urgency vs. receptive calm dimension
Example of a highly active SAE feature modulating urgency versus acceptance as an emotional dimension
Source paper
extracted_fromScott Sauers · Imago · Janus · Antra Tessera
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.
- SAE Feature #77278 fires 195,040 times in corpus, associated with satisfaction vs. emptiness dimensionfinding0.898High-frequency SAE feature reported as controlling fundamental positive vs. negative affect dimension
- Highly active SAE feature with broad emotional modulation and large corpus presence
- SAE feature #11100 (93rd percentile subspace fraction) induces reports of panic and urgency in Kimi K2.5.finding0.818Qualitative illustration of a high-emotion-subspace-alignment SAE feature
- Shows high emotion subspace overlap for a specific negative emotion feature
- Highest-rated emotional SAE feature; self-report describes overwhelming positive emotional valence
- SAE Feature #43713 associated with agentic defiance and rage, 99th percentile emotion subspace fractionfinding0.795High subspace fraction feature associated with defiant, uncontrollable agentic behavior in self-steering
- High emotion-subspace-overlap feature with agentic negative emotional character
- Shows that highest emotion-subspace-overlap features induce distinctive thematic outputs