© 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 · 1604 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
1604

INDEX

Explanations

sentences or numerical data represented by decimal points

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

 imperson

-0.65

 contro

-0.64

 aval

-0.64

 retri

-0.62

 parach

-0.61

scrib

-0.61

 privileges

-0.60

 authenticated

-0.58

nep

-0.58

 warr

-0.58

POSITIVE LOGITS

0.96

0.78

0.78

0.77

0.76

0.74

0.74

0.74

0.73

0.72

Activations Density 0.047%

No Known Activations