INDEX

Explanations

clothing items or accessories

oai_token-act-pair · gpt-3.5-turbo

references to clothing or protective wear

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

llor

-0.87

terness

-0.83

 Dhabi

-0.77

ancock

-0.77

hesda

-0.76

emetery

-0.75

mble

-0.75

iets

-0.73

enario

-0.72

ezvous

-0.72

POSITIVE LOGITS

 clothes

1.01

 sleeves

1.00

 shirt

0.97

 camouflage

0.93

 dress

0.93

 jacket

0.93

 pants

0.92

 sleeve

0.91

 socks

0.91

 clipboard

0.89

Activations Density 0.128%

clothing items or accessories

references to clothing or protective wear

No Comments

No Known Activations