© 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 · 1343 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
1343

INDEX

Explanations

symbols or special characters in the text

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

interstitial

-0.83

mental

-0.67

 Proposition

-0.66

ipl

-0.65

termination

-0.65

alia

-0.64

adal

-0.64

uler

-0.61

 substance

-0.61

uman

-0.60

POSITIVE LOGITS

++;

0.68

�

0.68

inventoryQuantity

0.66

Fail

0.64

�

0.62

OTOS

0.62

�

0.60

 bliss

0.58

�

0.57

rador

0.57

Activations Density 0.290%

No Known Activations