INDEX

Explanations

medical conditions and related terms, particularly focused on diseases and disorders

oai_token-act-pair · gpt-3.5-turbo

occurrences of medical terms related to various diseases and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

soDeliveryDate

-0.94

displayText

-0.83

Lago

-0.75

selage

-0.73

saf

-0.72

Reward

-0.72

isSpecialOrderable

-0.71

 Mahjong

-0.70

 Catalog

-0.69

thouse

-0.69

POSITIVE LOGITS

 disease

1.48

 disorders

1.45

 diseases

1.45

 pneumonia

1.41

 illness

1.41

 syndrome

1.36

 sclerosis

1.32

 Syndrome

1.32

 illnesses

1.32

 dementia

1.31

Activations Density 0.242%

medical conditions and related terms, particularly focused on diseases and disorders

occurrences of medical terms related to various diseases and conditions

No Comments

No Known Activations