INDEX

Explanations

toggle switches or captions in images

oai_token-act-pair · gpt-3.5-turbo

instances of the word "toggle."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

bats

-0.69

umped

-0.68

rams

-0.67

dating

-0.65

ĪĴ

-0.64

esses

-0.63

DoS

-0.63

gang

-0.63

NN

-0.62

metic

-0.62

POSITIVE LOGITS

 toggle

1.12

 caption

0.82

Enlarge

0.78

 Thumbnails

0.74

pmwiki

0.72

 "$:/

0.72

toggle

0.70

taboola

0.70

Pinterest

0.69

 WATCHED

0.68

Activations Density 0.003%

toggle switches or captions in images

instances of the word "toggle."

No Comments

No Known Activations