INDEX

Explanations

procedures, reports, and allegations listed in a document

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

 Aber

-0.78

irgin

-0.72

icago

-0.69

 Huck

-0.68

 Fine

-0.67

ione

-0.66

 Abbey

-0.66

idge

-0.66

Fine

-0.66

icer

-0.65

POSITIVE LOGITS

erv

1.30

lists

1.00

icles

1.00

icle

0.96

abet

0.92

ening

0.91

erve

0.90

ener

0.89

 comprehens

0.88

lessness

0.88

Activations Density 7.203%

procedures, reports, and allegations listed in a document

No Comments

No Known Activations