INDEX

Explanations

references to healthcare-related terms

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 @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Reloaded

-0.83

kat

-0.72

UA

-0.68

mini

-0.68

gren

-0.65

 Rubin

-0.63

 Slam

-0.63

itri

-0.62

Draft

-0.62

kan

-0.62

POSITIVE LOGITS

 care

3.71

 Care

2.60

care

2.36

 cared

2.25

 CARE

2.12

 cares

1.99

 caring

1.99

Care

1.85

 caregivers

1.35

 careg

1.32

Activations Density 0.022%

references to healthcare-related terms

references to health care topics

No Comments

No Known Activations