INDEX

Explanations

details related to technology features and reviews in smartphones and electronic devices

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

interrupted

-0.36

den

-0.32

rans

-0.31

liam

-0.29

Department

-0.29

Reports

-0.28

 coun

-0.28

liter

-0.27

RN

-0.27

 Liter

-0.27

POSITIVE LOGITS

 notch

0.35

 jewel

0.35

iest

0.34

 feather

0.34

 loot

0.34

 jewels

0.33

 sticking

0.33

 juicy

0.33

 ballpark

0.32

pie

0.31

Activations Density 13.469%

details related to technology features and reviews in smartphones and electronic devices

No Comments

No Known Activations