INDEX

Explanations

dates mentioned in parentheses

oai_token-act-pair · gpt-3.5-turbo

opening parentheses in text

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

 everyday

-0.80

 untreated

-0.76

 deport

-0.73

wre

-0.72

 imperson

-0.71

 retard

-0.71

 overpower

-0.71

 intangible

-0.71

 extingu

-0.71

 mature

-0.71

POSITIVE LOGITS

pictured

1.36

which

1.34

see

1.34

via

1.30

although

1.25

PDF

1.24

pdf

1.24

thanks

1.22

sic

1.22

http

1.22

Activations Density 0.166%

dates mentioned in parentheses

opening parentheses in text

No Comments

No Known Activations