INDEX

Explanations

technical patterns or code snippets within text, potentially related to programming or markup languages

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

soDeliveryDate

-0.39

 Canaver

-0.37

 Cosponsors

-0.31

emonium

-0.31

ãĥ¼ãĥ³

-0.29

Eag

-0.28

afety

-0.28

ctuary

-0.28

BuyableInstoreAndOnline

-0.28

etheless

-0.28

POSITIVE LOGITS

 cane

0.34

 chewing

0.30

dry

0.29

 bladder

0.29

lim

0.29

 thirst

0.28

 chop

0.28

hyd

0.28

por

0.28

 toilet

0.28

Activations Density 4.246%

technical patterns or code snippets within text, potentially related to programming or markup languages

No Comments

No Known Activations