INDEX

Explanations

phrases related to specific cities or locations

oai_token-act-pair · gpt-3.5-turbo

references to various cities

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

ateral

-0.72

<?

-0.70

catentry

-0.68

ACE

-0.66

MpServer

-0.66

wcs

-0.66

 recite

-0.65

NetMessage

-0.65

lass

-0.64

 topical

-0.64

POSITIVE LOGITS

 Indianapolis

0.92

 Cincinnati

0.90

 Atlanta

0.88

 Warwick

0.88

 Naples

0.86

 Tulsa

0.85

 Janeiro

0.82

 Seattle

0.82

 Burlington

0.81

 Spokane

0.81

Activations Density 0.050%

phrases related to specific cities or locations

references to various cities

No Comments

No Known Activations