INDEX

Explanations

expressions of hope or wishes

oai_token-act-pair · gpt-3.5-turbo

expressions of hope

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

pes

-0.78

ItemImage

-0.73

cial

-0.72

eas

-0.71

atures

-0.70

chem

-0.68

alties

-0.66

cler

-0.66

versions

-0.65

 Peninsula

-0.63

POSITIVE LOGITS

 someday

1.06

 somebody

0.76

you

0.71

 whoever

0.70

fully

0.68

 unborn

0.67

 someone

0.66

 expr

0.65

 readers

0.62

imaru

0.62

Activations Density 0.028%

expressions of hope or wishes

expressions of hope

No Comments

No Known Activations