© 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 · 960 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
960

INDEX

Explanations

phrases indicating subjects or topics of significance

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

 Carbuncle

-0.82

���

-0.72

etheless

-0.70

 concoct

-0.66

soever

-0.65

 defer

-0.64

��

-0.63

theless

-0.62

 Notting

-0.61

 Inher

-0.60

POSITIVE LOGITS

AZ

0.78

ODY

0.73

borg

0.71

Es

0.69

Kit

0.69

Wan

0.68

Privacy

0.67

Jr

0.67

ITAL

0.66

 immortality

0.66

Activations Density 0.022%

No Known Activations