© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

GPT2-SMALL · 8-TRES-DC · 1331 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
1331

INDEX

Explanations

phrases that question the existence or importance of something

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

tnc

-0.70

irtual

-0.69

EStream

-0.67

que

-0.67

ylum

-0.66

EStreamFrame

-0.65

yip

-0.63

quickShipAvailable

-0.63

Temperature

-0.62

ESA

-0.62

POSITIVE LOGITS

 alike

0.66

along

0.59

guide

0.59

 analy

0.58

 Printing

0.57

imer

0.57

 recalls

0.57

ations

0.57

andr

0.56

 bind

0.56

Activations Density 0.024%

No Known Activations