INDEX

Explanations

discussions and content regarding international conflicts and diplomatic relations

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

 nipples

-0.59

().

-0.57

 monog

-0.57

 darn

-0.57

().

-0.54

 damned

-0.54

 thereof

-0.53

 dudes

-0.53

 EVERY

-0.52

 ðŁĻĤ

-0.52

POSITIVE LOGITS

resa

1.11

odore

0.88

ogether

0.75

intendent

0.74

nsic

0.73

romeda

0.70

 spokeswoman

0.69

alyst

0.69

gency

0.69

wards

0.68

Activations Density 13.573%

discussions and content regarding international conflicts and diplomatic relations

No Comments

No Known Activations