INDEX

Explanations

references to geographical locations and political 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

wagen

-0.72

DonaldTrump

-0.65

vertisement

-0.64

«ĺ

-0.63

aimon

-0.63

idates

-0.61

phia

-0.59

 sucker

-0.58

 exha

-0.58

animous

-0.58

POSITIVE LOGITS

enegger

1.01

tons

0.91

ozy

0.86

arro

0.76

athan

0.75

arty

0.72

ingen

0.72

eday

0.71

yg

0.71

er

0.68

Activations Density 6.511%

references to geographical locations and political events

No Comments

No Known Activations