INDEX

Explanations

terms related to scientific and medical research, including genetics, neurology, and drug-induced effects

oai_token-act-pair · gpt-3.5-turbo

terms related to neurological functioning and memory

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

ilitary

-0.95

wered

-0.89

nces

-0.84

urches

-0.78

krit

-0.73

ulhu

-0.71

å¥³

-0.70

epad

-0.68

bah

-0.66

htaking

-0.66

POSITIVE LOGITS

 phenotype

1.14

 metabolism

1.01

 pathology

0.97

 outcomes

0.95

ogenesis

0.93

 susceptibility

0.90

 initiation

0.88

 behaviors

0.88

 disorders

0.87

 cognition

0.86

Activations Density 0.297%

terms related to scientific and medical research, including genetics, neurology, and drug-induced effects

terms related to neurological functioning and memory

No Comments

No Known Activations