INDEX

Explanations

mention and discussion of film characters and their relationships

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

Lear

-0.81

*/

-0.78

INTON

-0.76

------

-0.76

—-

-0.75

 prolet

-0.74

soever

-0.74

arming

-0.73

pled

-0.73

commit

-0.71

POSITIVE LOGITS

senal

1.20

rael

1.17

 hereby

1.08

 also

1.02

cussion

0.98

 pictured

0.96

 rated

0.95

ometric

0.95

 currently

0.95

 definitely

0.94

Activations Density 2.215%

mention and discussion of film characters and their relationships

No Comments

No Known Activations