INDEX

Explanations

specific names and terms, such as people's names and company 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

gerald

-0.92

ippi

-0.83

afety

-0.80

ODUCT

-0.76

soDeliveryDate

-0.73

ledged

-0.73

dds

-0.73

anim

-0.72

é»Ĵ

-0.71

stakes

-0.70

POSITIVE LOGITS

 Turing

1.09

tering

0.89

Lev

0.83

 Gross

0.83

isen

0.82

 Watts

0.82

ization

0.82

ists

0.77

 Wake

0.77

 Shepard

0.77

Activations Density 5.081%

specific names and terms, such as people's names and company names

No Comments

No Known Activations