INDEX

Explanations

phrases related to clothing items

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Creed

-0.77

 Occupations

-0.66

CLASSIFIED

-0.60

enegger

-0.56

schild

-0.55

 Chronicle

-0.55

paces

-0.54

 Oath

-0.53

 Fired

-0.53

 Hitman

-0.53

POSITIVE LOGITS

ela

0.83

oling

0.77

arella

0.77

eline

0.73

ua

0.72

illo

0.72

lov

0.71

uan

0.69

aea

0.68

eson

0.67

Activations Density 0.134%

phrases related to clothing items

No Comments

No Known Activations