INDEX

Explanations

mentions of the concept of universality

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

inventoryQuantity

-1.33

utenant

-1.25

Else

-1.21

--------------------------------------------------------

-1.19

à©

-1.14

mosp

-1.11

Khe

-1.07

xual

-1.06

llo

-1.03

cano

-1.03

POSITIVE LOGITS

ities

1.87

idad

1.66

itarian

1.65

ITY

1.63

ity

1.63

itÃ©

1.49

isation

1.44

isable

1.38

ization

1.38

ized

1.37

Activations Density 0.989%

mentions of the concept of universality

No Comments

No Known Activations