INDEX

Explanations

proper nouns, specifically names and places

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

mot

-0.64

æ©

-0.64

Xi

-0.63

 abdom

-0.63

Balt

-0.63

¶æ

-0.62

Ct

-0.62

Quote

-0.62

 magnification

-0.61

SpaceEngineers

-0.61

POSITIVE LOGITS

ufact

0.74

arella

0.73

vu

0.73

assador

0.72

uku

0.71

culosis

0.71

hof

0.69

ouf

0.65

zee

0.65

vity

0.64

Activations Density 0.281%

proper nouns, specifically names and places

proper nouns and names of individuals

No Comments

No Known Activations