© 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 · 175 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
175

INDEX

Explanations

comparisons and expressions of proximity or similarity

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

igmatic

-0.79

atown

-0.77

htaking

-0.75

senal

-0.71

OTOS

-0.66

 Signs

-0.66

legraph

-0.66

gage

-0.65

udic

-0.65

APD

-0.65

POSITIVE LOGITS

 discharged

0.70

cot

0.64

 stret

0.62

edited

0.61

 CARE

0.61

 aptly

0.59

 depart

0.59

 wanna

0.58

RL

0.58

 tram

0.58

Activations Density 0.099%

No Known Activations