INDEX

Explanations

questions beginning with 'How'

oai_token-act-pair · gpt-3.5-turbo

questions starting with "How"

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

Ãį

-0.65

agonists

-0.63

iculture

-0.62

-0.61

 receiving

-0.59

ceptions

-0.59

 fide

-0.59

uthor

-0.59

IENT

-0.58

otor

-0.56

POSITIVE LOGITS

soever

1.13

ever

0.94

beit

0.92

ling

0.76

leep

0.74

ells

0.74

HCR

0.73

ls

0.71

itzer

0.70

bill

0.68

Activations Density 0.064%

questions beginning with 'How'

questions starting with "How"

No Comments

No Known Activations