INDEX

Explanations

code structures and technical terms found in programming

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

 Clarkson

-0.66

 Ferry

-0.65

 Wynne

-0.64

 curfew

-0.63

DOE

-0.62

cale

-0.61

 Giles

-0.59

peed

-0.59

 overboard

-0.58

 clutch

-0.58

POSITIVE LOGITS

urally

1.48

uring

1.21

ured

1.17

urer

1.09

uration

1.02

rait

1.01

ript

0.97

ures

0.97

urers

0.95

ural

0.94

Activations Density 6.374%

code structures and technical terms found in programming

No Comments

No Known Activations