INDEX

Explanations

information related to international relations, specifically focusing on diplomatic interactions and territorial disputes in the Asia-Pacific region

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bats

-0.74

asonable

-0.70

Rog

-0.67

Typ

-0.66

 Hitchcock

-0.66

Fen

-0.65

Ob

-0.64

 Hopkins

-0.63

raviolet

-0.62

 Manit

-0.62

POSITIVE LOGITS

 region

0.87

 countries

0.85

 Cooperation

0.85

 superpower

0.84

 nations

0.78

istan

0.78

 peace

0.74

 borders

0.72

 destinations

0.72

 economies

0.72

Activations Density 9.300%

information related to international relations, specifically focusing on diplomatic interactions and territorial disputes in the Asia-Pacific region

No Comments

No Known Activations