INDEX

Explanations

medical terms related to abnormal conditions or dysfunctions in the body

oai_token-act-pair · gpt-3.5-turbo

terms related to abnormalities and disorders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ofi

-0.81

soDeliveryDate

-0.77

-0.73

roc

-0.69

 Hancock

-0.66

riel

-0.65

yright

-0.65

liner

-0.64

Phil

-0.63

ndra

-0.63

POSITIVE LOGITS

 worsen

0.93

 abnormal

0.85

 impair

0.85

 predis

0.83

 inflammation

0.82

 abnormalities

0.81

 lesions

0.80

 epile

0.80

 susceptibility

0.80

 deterior

0.79

Activations Density 0.062%

medical terms related to abnormal conditions or dysfunctions in the body

terms related to abnormalities and disorders

No Comments

No Known Activations