INDEX

Explanations

content related to health and health insurance

oai_token-act-pair · gpt-3.5-turbo

references to health-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

xual

-0.80

yip

-0.79

 Helpful

-0.76

 Reloaded

-0.73

arget

-0.72

Duo

-0.70

toe

-0.68

coni

-0.68

 teasp

-0.68

venants

-0.67

POSITIVE LOGITS

care

1.16

 care

1.15

Care

0.99

 Care

0.99

iest

0.96

 insurance

0.94

amacare

0.92

aceutical

0.91

span

0.88

 insurers

0.86

Activations Density 0.032%

content related to health and health insurance

references to health-related topics

No Comments

No Known Activations