INDEX

Explanations

words related to clothing or garments

oai_token-act-pair · gpt-3.5-turbo

mentions of clothing items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Kern

-0.65

 probable

-0.64

Iraq

-0.63

AUT

-0.63

Rare

-0.61

CVE

-0.60

 paraph

-0.60

Trust

-0.59

 Democr

-0.59

SPONSORED

-0.59

POSITIVE LOGITS

 clothes

1.19

 garments

1.10

 apparel

1.06

 clothing

1.05

leeve

1.00

puter

0.99

pins

0.99

 trousers

0.98

 shoes

0.98

 Clothing

0.96

Activations Density 0.009%

words related to clothing or garments

mentions of clothing items

No Comments

No Known Activations