INDEX

Explanations

Keywords related to healthcare and health policy

oai_token-act-pair · gpt-3.5-turbo

references to health care topics

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

urat

-0.79

Publisher

-0.75

 Reloaded

-0.71

 Jungle

-0.69

selves

-0.66

toe

-0.63

WithNo

-0.63

umar

-0.62

akedown

-0.62

 Goodwin

-0.62

POSITIVE LOGITS

 care

1.46

care

1.34

 insurance

1.31

 Care

1.22

Care

1.19

 insurers

1.06

 insurer

1.06

 Insurance

1.00

iest

0.98

amacare

0.97

Activations Density 0.034%

Keywords related to healthcare and health policy

references to health care topics

No Comments

No Known Activations