© 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 · 2824 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
2824

INDEX

Explanations

repeated references to a specific name or term

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

raviolet

-0.74

 diving

-0.65

icably

-0.64

 bidder

-0.63

 converting

-0.61

cffff

-0.59

 bindings

-0.59

Eag

-0.59

 chopping

-0.59

Fib

-0.59

POSITIVE LOGITS

enegger

0.94

old

0.87

inals

0.84

oya

0.83

allo

0.81

lette

0.79

eu

0.76

lest

0.76

cn

0.71

borgh

0.69

Activations Density 0.036%

No Known Activations