© 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 · 1280 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
1280

INDEX

Explanations

numerical data and time-related information

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

UGE

-0.78

aneously

-0.77

=-=-

-0.75

izen

-0.71

nesty

-0.67

esley

-0.66

-0.65

cro

-0.65

izens

-0.65

lore

-0.65

POSITIVE LOGITS

 polyg

0.72

 Surviv

0.68

 Simulator

0.66

 assignment

0.64

 expectation

0.64

 mouths

0.61

 commentary

0.61

 prediction

0.60

 duty

0.60

 comprehension

0.59

Activations Density 0.063%

No Known Activations