INDEX

Explanations

people's names, particularly focusing on the name "Adriana."

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

é¾

-1.30

 Brunswick

-1.12

 Pengu

-1.03

 Moroc

-1.02

 Fiorina

-1.02

 chips

-1.02

manship

-1.02

 magnification

-1.01

rights

-1.00

 convol

-0.99

POSITIVE LOGITS

ving

1.76

zzle

1.74

quet

1.56

quez

1.55

ety

1.50

ude

1.41

Äĩ

1.41

erer

1.40

zona

1.39

etta

1.39

Activations Density 0.526%

people's names, particularly focusing on the name "Adriana."

No Comments

No Known Activations