INDEX

Explanations

phrases related to dynamic and vivid descriptions of surroundings and experiences

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

atchewan

-0.55

sonian

-0.51

oug

-0.49

ractive

-0.48

orney

-0.45

 DEFENSE

-0.45

awar

-0.45

ãĥīãĥ©

-0.45

umo

-0.45

ĸļå£«

-0.45

POSITIVE LOGITS

 expectancy

0.63

lihood

0.58

forms

0.56

blood

0.56

liness

0.56

guards

0.55

boats

0.54

boat

0.52

guard

0.50

 indoors

0.47

Activations Density 9.701%

phrases related to dynamic and vivid descriptions of surroundings and experiences

No Comments

No Known Activations