© 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 · 1911 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
1911

INDEX

Explanations

terms related to various types of legislative acts and protections

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

Leaks

-0.67

BDS

-0.64

Afee

-0.64

 Playboy

-0.63

;;;;;;;;;;;;

-0.62

 Adidas

-0.61

Friend

-0.58

 Younger

-0.57

 displeasure

-0.57

andals

-0.56

POSITIVE LOGITS

oha

0.85

orah

0.77

wered

0.77

tn

0.74

oe

0.71

staking

0.71

cro

0.70

ara

0.70

verson

0.70

eyed

0.70

Activations Density 0.121%

No Known Activations