INDEX

Explanations

topics related to international relations and political conflicts, including discussions about specific countries, politicians, wars, and global events

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

 Increases

-0.69

Column

-0.62

MN

-0.58

VIDIA

-0.58

ami

-0.56

Cooldown

-0.56

Font

-0.56

rising

-0.55

:{

-0.55

margin

-0.54

POSITIVE LOGITS

 accountable

0.85

 into

0.75

 closer

0.73

 obsolete

0.72

 offline

0.70

selves

0.69

 away

0.68

 safely

0.67

 afloat

0.67

 hostage

0.67

Activations Density 14.021%

topics related to international relations and political conflicts, including discussions about specific countries, politicians, wars, and global events

No Comments

No Known Activations