INDEX

Explanations

terms related to neurological conditions such as Alzheimer's and Parkinson's disease

oai_token-act-pair · gpt-3.5-turbo

mentions of Alzheimer's disease and related dementias

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

-0.74

hops

-0.71

ellation

-0.70

soDeliveryDate

-0.67

Sources

-0.65

 Zoro

-0.64

ourced

-0.63

Fed

-0.63

ded

-0.63

 unreal

-0.62

POSITIVE LOGITS

 Alzheimer

1.10

 dementia

0.98

 disease

0.95

 Disease

0.90

esity

0.81

clerosis

0.80

thal

0.79

iac

0.74

 illness

0.74

 suff

0.72

Activations Density 0.009%

terms related to neurological conditions such as Alzheimer's and Parkinson's disease

mentions of Alzheimer's disease and related dementias

No Comments

No Known Activations