INDEX

Explanations

words related to enhancing or modifying something to improve its quality or performance

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

 Daylight

-0.56

 Kills

-0.55

enegger

-0.52

 Alma

-0.52

DERR

-0.51

 Reborn

-0.49

 Fallon

-0.49

ORGE

-0.48

 Letter

-0.47

 Participant

-0.47

POSITIVE LOGITS

roying

0.83

itored

0.78

tenance

0.78

ility

0.76

aring

0.74

orting

0.72

ensing

0.71

avored

0.71

ruction

0.70

acters

0.69

Activations Density 4.375%

words related to enhancing or modifying something to improve its quality or performance

No Comments

No Known Activations