INDEX

Explanations

names of organizations, groups, and entities

oai_token-act-pair · gpt-3.5-turbo

references to organizations and institutional entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 eternity

-0.68

fitting

-0.62

ãĤ¯

-0.58

 Brow

-0.57

ãĤ´ãĥ³

-0.56

é¾įå¥ĳå£«

-0.56

ãĤ¨ãĥ«

-0.48

ãģĦ

-0.48

zac

-0.48

igen

-0.47

POSITIVE LOGITS

has

0.84

had

0.83

 went

0.82

 reacted

0.79

 took

0.76

 gave

0.76

 cannot

0.76

 recognizes

0.75

 grew

0.75

 fared

0.75

Activations Density 0.962%

names of organizations, groups, and entities

references to organizations and institutional entities

No Comments

No Known Activations