INDEX

Explanations

references to activities or actions related to sleep, work, or daily routines in various contexts

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

IFrame

Link

Negative Logits

DragonMagazine

-0.29

 Primordial

-0.29

stood

-0.27

reviewed

-0.26

Ps

-0.26

 Bagg

-0.26

 exception

-0.25

 Twin

-0.24

 Thousand

-0.24

 Neph

-0.24

POSITIVE LOGITS

aturday

0.36

aturdays

0.34

night

0.33

 Skydragon

0.32

ername

0.32

IFA

0.32

ADRA

0.30

hesda

0.29

miah

0.27

heet

0.27

Activations Density 0.234%

references to activities or actions related to sleep, work, or daily routines in various contexts

No Known Activations