INDEX

Explanations

references to arguments and debates

oai_token-act-pair · gpt-3.5-turbo

patterns related to risk and evidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Cosponsors

-0.57

ß

-0.57

asketball

-0.55

ather

-0.54

auri

-0.54

estern

-0.53

 partName

-0.51

oulos

-0.51

cohol

-0.50

 Adin

-0.50

POSITIVE LOGITS

 thereof

0.97

 theirs

0.96

 them

0.96

 thereto

0.87

it

0.79

 accordingly

0.78

 hers

0.74

 therein

0.73

 THEM

0.71

 afterwards

0.64

Activations Density 1.967%

references to arguments and debates

patterns related to risk and evidence

No Comments

No Known Activations