INDEX

Explanations

instances of collaboration or teamwork

oai_token-act-pair · gpt-3.5-turbo

the conjunction "and" used in various contexts

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

DragonMagazine

-0.89

uct

-0.75

LOCK

-0.72

actionDate

-0.68

GMT

-0.67

BL

-0.67

lav

-0.66

SPA

-0.65

wat

-0.65

ks

-0.63

POSITIVE LOGITS

 thereby

1.31

 thus

1.27

 consequently

1.25

 hence

1.12

 therefore

1.10

 encourages

0.93

 furthermore

0.92

 vice

0.91

 THEN

0.87

 interacts

0.86

Activations Density 0.374%

instances of collaboration or teamwork

the conjunction "and" used in various contexts

No Comments

No Known Activations