INDEX

Explanations

sequences of characters that represent a specific language or script

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

nect

-0.94

inately

-0.92

netic

-0.86

istically

-0.86

fman

-0.83

enton

-0.83

ansas

-0.81

glers

-0.81

onomy

-0.81

iop

-0.79

POSITIVE LOGITS

³

0.90

Ö¼

0.80

Į

0.80

×ª

0.78

Ĥª

0.78

²

0.76

´

0.74

¸

0.72

æĸ¹

0.72

¡

0.72

Activations Density 6.543%

sequences of characters that represent a specific language or script

No Comments

No Known Activations