INDEX

Explanations

passages related to political events and news

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

ibrary

-0.33

DonaldTrump

-0.31

 Bulgar

-0.28

uchin

-0.28

 Aval

-0.27

xia

-0.27

ItemTracker

-0.27

 TODAY

-0.26

ÃŁ

-0.26

 Hung

-0.26

POSITIVE LOGITS

 alike

0.71

 thereof

0.67

 accordingly

0.63

 respectively

0.62

 thereafter

0.59

 thereto

0.53

 therein

0.52

 versa

0.48

 attRot

0.41

 afterward

0.40

Activations Density 46.970%

passages related to political events and news

No Comments

No Known Activations