INDEX

Explanations

proper nouns and specific terms related to individuals, companies, and organizations

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

IONS

-0.95

wich

-0.89

otiation

-0.86

WithNo

-0.84

iage

-0.83

earchers

-0.81

 rall

-0.81

ather

-0.80

ODUCT

-0.80

thur

-0.80

POSITIVE LOGITS

 Beir

0.84

Fey

0.84

ERY

0.82

lift

0.78

ilation

0.77

inous

0.75

 Tribune

0.73

rous

0.73

 Jensen

0.72

Der

0.71

Activations Density 8.321%

proper nouns and specific terms related to individuals, companies, and organizations

No Comments

No Known Activations