INDEX

Explanations

references to the concept of blindness or things that are obscured from view

oai_token-act-pair · gpt-3.5-turbo

instances of the word "blind" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

xit

-0.95

 Occupations

-0.82

OPLE

-0.73

ICAN

-0.71

ALLY

-0.70

CE

-0.69

AIN

-0.66

OTHER

-0.64

HOU

-0.64

akeru

-0.62

POSITIVE LOGITS

sight

1.30

sided

1.28

fold

1.28

blind

1.15

sighted

1.00

 blind

0.97

ingly

0.97

eyed

0.96

ibility

0.94

poke

0.91

Activations Density 0.028%

references to the concept of blindness or things that are obscured from view

instances of the word "blind" in various contexts

No Comments

No Known Activations