INDEX

Explanations

information related to video game features and updates

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

KEY

-0.66

Ph

-0.56

Nap

-0.56

tu

-0.54

PIN

-0.52

err

-0.50

pu

-0.48

 Prairie

-0.48

heart

-0.48

kil

-0.48

POSITIVE LOGITS

tenance

0.97

terday

0.93

osterone

0.77

llor

0.76

xual

0.74

theless

0.71

lihood

0.70

amental

0.69

acters

0.66

yright

0.65

Activations Density 13.640%

information related to video game features and updates

No Comments

No Known Activations