INDEX

Explanations

phrases related to individuals and organizations

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

egg

-0.45

VERTISEMENT

-0.43

resources

-0.43

ergy

-0.42

pection

-0.42

phal

-0.42

zac

-0.41

BAT

-0.41

gif

-0.40

oult

-0.40

POSITIVE LOGITS

 Lynch

0.43

 Lynn

0.41

tta

0.39

elly

0.37

erest

0.37

 Dame

0.36

icated

0.36

arians

0.36

zyk

0.35

 Thatcher

0.35

Activations Density 7.532%

phrases related to individuals and organizations

No Comments

No Known Activations