© 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 · 361 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
361

INDEX

Explanations

references to political ideologies and affiliations

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

available

-0.83

}}}

-0.68

OUNT

-0.63

++++

-0.62

 inev

-0.61

oise

-0.61

ound

-0.60

ulkan

-0.60

ector

-0.59

 icon

-0.59

POSITIVE LOGITS

ded

0.71

alties

0.67

 consulting

0.65

 sqor

0.61

 Sons

0.59

 Marriott

0.57

ufact

0.57

bol

0.57

 Winter

0.57

eger

0.56

Activations Density 0.168%

No Known Activations