INDEX

Explanations

positive affirmations and optimistic statements

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

CAST

-0.88

spread

-0.76

hips

-0.75

worthiness

-0.74

Â¯

-0.74

rats

-0.73

orns

-0.72

ses

-0.72

tub

-0.70

ifier

-0.70

POSITIVE LOGITS

Page

0.85

 Page

0.83

 Islands

0.82

olitics

0.72

agle

0.70

veyard

0.70

 Downs

0.70

Ń·

0.68

Down

0.67

uthor

0.66

Activations Density 0.233%

positive affirmations and optimistic statements

No Comments

No Known Activations