© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GPT2-SMALL · 8-TRES-DC · 745 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
745

INDEX

Explanations

numerical data related to quantities and measurements

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

Not in Any Lists

No Comments

Negative Logits

 urges

-0.64

arten

-0.61

 begged

-0.61

anthrop

-0.61

...]

-0.61

ECA

-0.59

leck

-0.59

 motiv

-0.59

 lest

-0.57

 communicates

-0.56

POSITIVE LOGITS

ェ

0.67

dash

0.67

ts

0.65

cv

0.64

uka

0.63

nex

0.63

round

0.62

isal

0.62

ftime

0.61

adic

0.61

Activations Density 0.146%

No Known Activations