© 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 · 1402 ｜ Neuronpedia

Home
GPT2-Small
Transcoders Residuals
8-TRES-DC
1402

INDEX

Explanations

repeated instances of the word "the" in various 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

rists

-0.71

oos

-0.68

rie

-0.67

aus

-0.66

waters

-0.66

onite

-0.66

apo

-0.64

olves

-0.64

makers

-0.64

iences

-0.64

POSITIVE LOGITS

 normalized

0.84

 stride

0.77

 configured

0.74

 given

0.73

 actionGroup

0.71

 wrapped

0.70

 corresponding

0.69

 formatted

0.68

 clad

0.67

 tagged

0.67

Activations Density 0.138%

No Known Activations