© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

GPT2-SMALL · 8-TRES-DC · 3042 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
3042

INDEX

Explanations

occurrences of the word "test" and its variations in different contexts

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

 Clicker

-0.82

 McKenna

-0.73

 todd

-0.72

 Lange

-0.70

SHARE

-0.69

 Wasserman

-0.68

Pin

-0.68

 Feld

-0.66

 Volunte

-0.66

 POLITICO

-0.65

POSITIVE LOGITS

qqa

0.79

0.77

aea

0.74

ivo

0.73

yne

0.73

icular

0.71

chens

0.70

urbed

0.69

mone

0.68

 consequences

0.68

Activations Density 0.031%

No Known Activations