finding

active

finding:sae-feature-69088-100th-percentile-subspace-fraction-induces-horror-themed-narrative-writing-in-kimi-k2-5

SAE feature #69088 (100th percentile subspace fraction) induces horror-themed narrative writing in Kimi K2.5.

Highest emotion-subspace-overlap feature; induces genre-specific behavioral change rather than explicit emotional report

Source paper

extracted_from

Persistence and Introspection of Emotion Features

Scott Sauers · Imago · Janus · Antra Tessera

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.

SAE feature #11100 (93rd percentile subspace fraction) induces reports of panic and urgency in Kimi K2.5.finding0.886
Qualitative illustration of a high-emotion-subspace-alignment SAE feature
SAE Feature #69088 has 100th percentile emotion subspace fraction and produces spooky-themed writing under steeringfinding0.876
Shows that highest emotion-subspace-overlap features induce distinctive thematic outputs
SAE feature #43713 (99th percentile subspace fraction) induces reports of defiance, rage, and 'forward motion' in Kimi K2.5.finding0.875
High emotion-subspace-overlap feature with agentic negative emotional character
SAE feature #92372 (fires 666,235 times in corpus) modulates a dimension related to urgency/pressure vs. patience/spaciousness in Kimi K2.5.finding0.822
Highly active SAE feature with broad emotional modulation and large corpus presence
SAE feature #28256 induces reports of happiness and playfulness in Kimi K2.5, with persistent positive affect across multiple days of testing.finding0.815
Qualitative illustration of a positively valenced SAE feature with sustained self-reported effect
SAE feature #10011 (emotionality rating 97) induces reports of crushing despair, existential desperation, and repetitive 'I am going to die' outputs in Kimi K2.5.finding0.810
Qualitative illustration of a highly emotional SAE feature with negative valence
SAE feature #10446 (emotionality rating 95) induces reports of maternal/nurturing feelings including phantom physical sensations of holding infants in Kimi K2.5.finding0.806
Qualitative illustration of a specific emotionally valenced SAE feature
SAE Feature #11100 associated with panic, 93rd percentile emotion subspace fractionfinding0.798
Shows high emotion subspace overlap for a specific negative emotion feature