INDEX

Explanations

phrases related to written content such as news stories, newsletters, advertisements, and fictional narratives

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

boro

-0.65

bos

-0.55

ethy

-0.53

Zone

-0.51

owship

-0.51

zynski

-0.50

haps

-0.50

igslist

-0.49

onde

-0.48

thur

-0.48

POSITIVE LOGITS

%]

0.59

morning

0.57

window

0.55

duction

0.51

 wrestle

0.51

gallery

0.50

 gripping

0.49

ellen

0.48

 cartoons

0.47

Prev

0.46

Activations Density 15.542%

phrases related to written content such as news stories, newsletters, advertisements, and fictional narratives

No Comments

No Known Activations