INDEX

Explanations

phrases related to policies, government actions, and international 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

eer

-0.99

ger

-0.73

 Parenthood

-0.73

 Pirate

-0.72

 Times

-0.72

amins

-0.72

mails

-0.69

Ing

-0.68

Voy

-0.68

LY

-0.67

POSITIVE LOGITS

 speaking

1.11

 challeng

0.95

 sourced

0.90

 conclud

0.90

 minded

0.90

 housed

0.89

 produced

0.89

 identifiable

0.89

 priced

0.89

speaking

0.88

Activations Density 7.046%

phrases related to policies, government actions, and international relations

No Comments

No Known Activations