INDEX

Explanations

people's names and titles in news articles

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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

ĸļ

-0.88

ãĤ¤ãĥĪ

-0.86

 sidx

-0.79

DragonMagazine

-0.75

CPC

-0.74

sburgh

-0.74

andise

-0.73

uyomi

-0.72

allery

-0.71

INGS

-0.71

POSITIVE LOGITS

legate

1.22

utsch

1.21

leted

1.21

bris

1.18

arest

1.16

legates

1.12

cember

1.09

vers

1.09

VICE

1.08

forestation

1.08

Activations Density 10.092%

people's names and titles in news articles

No Comments

No Known Activations