Neuronpedia

APISteer SAE Evals Blog/PodcastNEW Slack Privacy & Terms Contact

© Neuronpedia 2025

Privacy & Terms Blog/Podcast GitHub Slack Twitter Contact

Home
Dunefsky · Chlenski · Transcoders Enable Fine-Grained Interpretable Circuit Analysis
GPT2-Small
Transcoders Residuals
9-TRES-DC
645

INDEX

Explanations

mentions of Kansas City

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ptions

-0.74

bow

-0.71

ens

-0.69

astern

-0.68

meric

-0.67

back

-0.66

forth

-0.66

plet

-0.65

rell

-0.64

ende

-0.64

POSITIVE LOGITS

 City

0.93

 Soup

0.77

 CITY

0.75

Enh

0.65

 Puzzles

0.64

 skew

0.62

Zoo

0.61

 RELE

0.60

 gratification

0.59

 pleasing

0.59

Activations Density 0.063%

No Known Activations