© 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 · 3310 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
3310

INDEX

Explanations

the word "ever" 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

 Braun

-0.67

vere

-0.64

 Panc

-0.63

 Decay

-0.62

NX

-0.62

 upgr

-0.61

 Brawl

-0.60

 Beaver

-0.60

Dur

-0.60

aired

-0.59

POSITIVE LOGITS

toc

0.78

 clipboard

0.73

prus

0.72

anamo

0.71

nesia

0.70

pedia

0.68

audi

0.67

yss

0.67

accompan

0.65

umbnails

0.64

Activations Density 0.021%

No Known Activations