INDEX

Explanations

proper nouns related to governmental or legislative bodies

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

ept

-0.81

ghan

-0.76

xia

-0.73

ãģŁ

-0.72

ãģ¦

-0.69

uber

-0.69

plet

-0.68

TRUMP

-0.67

Complete

-0.65

imilar

-0.65

POSITIVE LOGITS

arians

1.56

arian

1.20

 Speaker

1.00

liament

0.94

 parliament

0.93

agall

0.92

bourg

0.90

 Buildings

0.87

yard

0.87

 Sabha

0.86

Activations Density 5.543%

proper nouns related to governmental or legislative bodies

No Comments

No Known Activations