INDEX

Explanations

mentions of the word "sign" used in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to signs and indications

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

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

»Ĵ

-0.70

 Remastered

-0.70

 DRAG

-0.68

ĸļ

-0.68

=~=~

-0.65

ETHOD

-0.63

ecause

-0.63

aundering

-0.62

ategory

-0.61

merce

-0.61

POSITIVE LOGITS

atories

1.36

posts

1.24

atory

1.12

ifiers

1.06

post

1.06

ifier

1.05

posted

1.03

atures

1.01

ifying

1.01

boards

1.00

Activations Density 0.034%

mentions of the word "sign" used in various contexts

references to signs and indications

No Comments

No Known Activations