© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

GPT2-SMALL · 8-TRES-DC · 3217 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
3217

INDEX

Explanations

phrases related to consequences and responses to events

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Negative Logits

INGTON

-0.56

 constit

-0.56

 kindred

-0.53

 oneself

-0.51

Duo

-0.51

 curfew

-0.50

 flaw

-0.50

idon

-0.50

 staying

-0.50

 constituent

-0.49

POSITIVE LOGITS

sels

0.71

 thereto

0.69

hran

0.66

hered

0.65

oldown

0.65

azy

0.64

ablishment

0.63

berus

0.62

awn

0.62

to

0.61

Activations Density 0.243%

No Known Activations