INDEX

Explanations

phrases related to expansion or broadening of something

oai_token-act-pair · gpt-3.5-turbo

phrases indicating expansion or inclusion of elements or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

achev

-0.79

hester

-0.72

ato

-0.68

ese

-0.66

ety

-0.66

ritz

-0.66

luck

-0.65

achy

-0.65

tale

-0.64

emon

-0.64

POSITIVE LOGITS

 encompass

1.59

 include

1.36

 accommodate

1.02

 Include

0.95

 incorporate

0.94

 exclude

0.88

 encompasses

0.87

 involve

0.86

 neighboring

0.83

 other

0.82

Activations Density 0.142%

phrases related to expansion or broadening of something

phrases indicating expansion or inclusion of elements or categories

No Comments

No Known Activations