© 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 · 3132 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
3132

INDEX

Explanations

occurrences of the letter "M" in various contexts

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

 evid

-0.74

 detach

-0.71

Mai

-0.70

 EntityItem

-0.59

 Sakuya

-0.59

 separ

-0.59

 camouflage

-0.59

 dispers

-0.58

 override

-0.57

 spawn

-0.57

POSITIVE LOGITS

istle

0.99

ural

0.99

aternity

0.91

ango

0.90

ornings

0.90

essed

0.89

ixtape

0.87

olic

0.87

ethyl

0.86

ixt

0.86

Activations Density 0.022%

No Known Activations