INDEX

Explanations

words related to the action of wearing something

oai_token-act-pair · gpt-3.5-turbo

words related to wearing and the condition of items that have been worn

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

aminer

-0.85

llor

-0.76

akespeare

-0.74

raction

-0.70

heid

-0.68

izoph

-0.66

ulhu

-0.66

yrinth

-0.65

ebus

-0.65

article

-0.65

POSITIVE LOGITS

 apparel

1.05

ables

1.04

 worn

1.00

 clothing

0.94

 underwear

0.93

 diapers

0.91

 gloves

0.87

 clothes

0.85

wear

0.84

 shoes

0.84

Activations Density 0.045%

words related to the action of wearing something

words related to wearing and the condition of items that have been worn

No Comments

No Known Activations