INDEX

Explanations

countries or specific locations

oai_token-act-pair · gpt-3.5-turbo

mentions of countries or geographical locations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

versions

-0.77

 sails

-0.65

bats

-0.65

essen

-0.63

 marvelous

-0.63

uebl

-0.62

ÃŁ

-0.62

ser

-0.61

 Dmit

-0.59

vae

-0.59

POSITIVE LOGITS

 Police

0.74

 Attorney

0.72

 Youth

0.72

 City

0.71

 Journalism

0.71

 Armed

0.70

 Telephone

0.69

 Rural

0.69

 Steel

0.68

 Cellular

0.67

Activations Density 0.449%

countries or specific locations

mentions of countries or geographical locations

No Comments

No Known Activations