© 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 · 3263 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
3263

INDEX

Explanations

mentions of news and related updates

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

 Keane

-0.65

atically

-0.65

 Mormonism

-0.61

 curses

-0.60

oyer

-0.59

itters

-0.58

 Inquisition

-0.58

 Applicant

-0.58

 doubt

-0.58

 Majesty

-0.57

POSITIVE LOGITS

gat

0.69

gor

0.69

gypt

0.69

enda

0.67

rand

0.66

nb

0.66

eret

0.66

orp

0.66

ru

0.66

fman

0.65

Activations Density 0.025%

No Known Activations