INDEX

Explanations

phrases related to meetings or encounters

oai_token-act-pair · gpt-3.5-turbo

the presence of non-standard or unusual compound words and phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SourceFile

-0.76

 Nare

-0.76

iott

-0.70

ongyang

-0.69

 nomine

-0.69

FS

-0.68

 Corpus

-0.66

ĸļ

-0.65

wcs

-0.62

 Seym

-0.61

POSITIVE LOGITS

advertising

1.00

exec

0.87

death

0.84

coord

0.83

gallery

0.80

distance

0.80

center

0.79

life

0.76

carry

0.76

function

0.75

Activations Density 0.034%

phrases related to meetings or encounters

the presence of non-standard or unusual compound words and phrases

No Comments

No Known Activations