INDEX

Explanations

proper nouns in a specific language

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

cean

-0.90

ptive

-0.85

pled

-0.84

undai

-0.84

ebus

-0.84

ptives

-0.83

culus

-0.81

pering

-0.80

cled

-0.80

yip

-0.78

POSITIVE LOGITS

ÑĮ

1.57

Ð¸

1.31

Ð¾Ð

1.26

Ð°

1.26

Ð¾

1.26

Ðµ

1.24

Ñı

1.21

Ð»

1.15

ĩ

1.13

Ñ

1.13

Activations Density 3.120%

proper nouns in a specific language

No Comments

No Known Activations