INDEX

Explanations

words and phrases related to automation

oai_token-act-pair · gpt-3.5-turbo

terms related to automation and automated processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

mary

-0.81

agne

-0.76

nah

-0.74

erva

-0.74

dn

-0.73

creen

-0.72

Magikarp

-0.72

eeper

-0.72

mond

-0.72

ented

-0.70

POSITIVE LOGITS

 automation

0.96

 automate

0.95

 autom

0.95

 automated

0.95

Autom

0.89

 captcha

0.84

 Autom

0.80

otive

0.78

 workforce

0.78

 locom

0.75

Activations Density 0.032%

words and phrases related to automation

terms related to automation and automated processes

No Comments

No Known Activations