INDEX

Explanations

first-person questions or uncertainties about various aspects of life and decision-making

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

xual

-0.99

ongyang

-0.97

kefeller

-0.91

culosis

-0.90

osterone

-0.88

 sheds

-0.88

 externalToEVAOnly

-0.88

 uranium

-0.84

 Regions

-0.84

 Sans

-0.84

POSITIVE LOGITS

azon

1.70

sterdam

1.37

ethyst

1.31

azes

1.29

ateurs

1.27

ajor

1.25

iller

1.20

estro

1.16

assing

1.16

 honored

1.13

Activations Density 0.613%

first-person questions or uncertainties about various aspects of life and decision-making

No Comments

No Known Activations