INDEX

Explanations

proper nouns, specifically names

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

ered

-0.71

ongyang

-0.70

ering

-0.66

resent

-0.66

rogen

-0.66

ple

-0.66

racted

-0.66

ramid

-0.66

href

-0.64

pled

-0.63

POSITIVE LOGITS

 Ashe

0.97

 Weasley

0.93

 Pend

0.83

 Conan

0.81

andise

0.76

 Arthur

0.75

itic

0.72

 Dent

0.69

ufact

0.68

beit

0.66

Activations Density 5.618%

proper nouns, specifically names

No Comments

No Known Activations