INDEX

Explanations

terms related to neurological diseases like Alzheimer's and Parkinson's

oai_token-act-pair · gpt-3.5-turbo

references to neurological 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Reviewer

-0.85

xtap

-0.84

 Zoro

-0.77

isSpecialOrderable

-0.73

Commerce

-0.72

 booth

-0.72

externalActionCode

-0.72

 Airbnb

-0.70

rolet

-0.69

ĳå£«

-0.69

POSITIVE LOGITS

 disease

1.52

 Disease

1.42

 diseases

1.26

 Syndrome

1.20

 disorders

1.17

 dementia

1.17

 syndrome

1.16

 illnesses

1.14

 illness

1.14

 diagnosis

1.12

Activations Density 0.139%

terms related to neurological diseases like Alzheimer's and Parkinson's

references to neurological diseases and conditions

No Comments

No Known Activations