INDEX

Explanations

mentions of specific individuals in political contexts, likely associated with opinions or analysis

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

ukong

-0.79

 Pony

-0.71

aimon

-0.70

amina

-0.70

 sacrific

-0.69

ickets

-0.66

 Samar

-0.66

 Vaugh

-0.66

alys

-0.65

unci

-0.65

POSITIVE LOGITS

ï¸ı

1.16

ï¸

0.92

âĢ¢âĢ¢

0.81

hazard

0.80

Ther

0.78

ternity

0.78

ÃĽ

0.76

ecause

0.75

Lic

0.74

Eight

0.70

Activations Density 10.917%

mentions of specific individuals in political contexts, likely associated with opinions or analysis

No Comments

No Known Activations