© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

GPT2-SMALL · 8-TRES-DC · 1325 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
1325

INDEX

Explanations

occurrences of the word "today" and its variations

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

kamp

-0.78

 Develop

-0.71

hops

-0.70

eries

-0.67

eners

-0.66

stals

-0.64

OW

-0.63

 delaying

-0.62

覚醒

-0.62

 Related

-0.60

POSITIVE LOGITS

verages

0.72

umption

0.69

eret

0.68

uably

0.66

plet

0.64

ugu

0.63

 ordinary

0.63

uga

0.62

most

0.62

 imitation

0.62

Activations Density 0.023%

No Known Activations