INDEX

Explanations

verbs related to utilizing or making use of something

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

 Empires

-0.34

 contag

-0.29

 Papers

-0.28

beans

-0.28

 Greenwood

-0.27

 Machines

-0.27

 Helsinki

-0.26

 mushroom

-0.26

 propel

-0.26

AAA

-0.26

POSITIVE LOGITS

uned

0.35

ken

0.33

rait

0.33

ãĥ¼ãĥ

0.33

uning

0.32

fully

0.32

esan

0.32

kt

0.32

ession

0.31

fulness

0.31

Activations Density 0.153%

verbs related to utilizing or making use of something

No Comments

No Known Activations