INDEX

Explanations

prepositions followed by a verb indicating movement or action

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Parents

-0.46

nah

-0.40

 influ

-0.38

FORE

-0.37

Bey

-0.37

 endors

-0.37

 Lauder

-0.37

 keyword

-0.37

Hur

-0.36

gel

-0.36

POSITIVE LOGITS

 rooft

0.54

hang

0.53

rocal

0.50

opia

0.48

ĸļ

0.44

oin

0.44

ales

0.43

asted

0.42

rights

0.42

PsyNetMessage

0.42

Activations Density 7.219%

prepositions followed by a verb indicating movement or action

No Comments

No Known Activations