INDEX

Explanations

phrases indicating multiple instances or occurrences 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

vest

-1.00

asta

-0.93

ittens

-0.91

NER

-0.90

bas

-0.89

amen

-0.89

Reviewer

-0.89

oper

-0.88

roit

-0.88

istan

-0.87

POSITIVE LOGITS

 hundred

1.99

 thousand

1.76

 dozen

1.69

 iterations

1.36

 occasions

1.28

 times

1.21

teenth

1.18

 months

1.17

 aspects

1.15

dozen

1.14

Activations Density 0.812%

phrases indicating multiple instances or occurrences of something

No Comments

No Known Activations