INDEX

Explanations

words related to journalism, media, and news reporting

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NetMessage

-0.95

arenthood

-0.92

 ..............

-0.90

ukong

-0.89

joice

-0.86

ignty

-0.85

è¦ļéĨĴ

-0.83

 Nirvana

-0.80

)",

-0.79

ahime

-0.79

POSITIVE LOGITS

 journalistic

0.88

 reader

0.88

 editorial

0.88

 archived

0.86

 readers

0.85

 publication

0.85

pdf

0.84

 archive

0.83

 publishing

0.82

 edits

0.82

Activations Density 11.052%

words related to journalism, media, and news reporting

No Comments

No Known Activations