© 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 · 1348 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
1348

INDEX

Explanations

titles and fields of academic professionals

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

rier

-0.72

forming

-0.65

croft

-0.64

 Nato

-0.64

lator

-0.61

warn

-0.61

txt

-0.60

ague

-0.60

rano

-0.60

suit

-0.60

POSITIVE LOGITS

 relate

0.68

 misunder

0.66

 exploitation

0.65

 Seym

0.64

 conflic

0.63

 embr

0.62

 suspic

0.62

¯¯

0.61

ETS

0.60

�

0.59

Activations Density 0.073%

No Known Activations