INDEX

Explanations

terms related to specific fields of study or professional areas

oai_token-act-pair · gpt-3.5-turbo

phrases related to specific academic fields or areas of study

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

vale

-0.73

 sqor

-0.63

nice

-0.63

orporated

-0.59

paces

-0.59

 waive

-0.59

istan

-0.58

 voic

-0.58

 reassuring

-0.58

 Waste

-0.57

POSITIVE LOGITS

 medicine

0.86

rency

0.71

lege

0.69

tains

0.65

oming

0.64

teenth

0.64

ellar

0.63

ãĤ¦ãĤ¹

0.62

lear

0.61

olls

0.61

Activations Density 0.089%

terms related to specific fields of study or professional areas

phrases related to specific academic fields or areas of study

No Comments

No Known Activations