INDEX

Explanations

phrases related to various medical conditions and diseases

oai_token-act-pair · gpt-3.5-turbo

terms associated with serious health conditions and diseases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

-0.98

agents

-0.85

soDeliveryDate

-0.83

ocrat

-0.83

uously

-0.81

âķĲ

-0.79

ezvous

-0.79

notations

-0.77

iquid

-0.76

uders

-0.76

POSITIVE LOGITS

 diabetes

1.59

 arthritis

1.56

 asthma

1.51

 hypertension

1.49

 pneumonia

1.42

 cardiovascular

1.38

 obesity

1.37

 allergies

1.36

 cancers

1.35

 tuberculosis

1.35

Activations Density 0.132%

phrases related to various medical conditions and diseases

terms associated with serious health conditions and diseases

No Comments

No Known Activations