INDEX

Explanations

technical information and data-related terms, like statistical measures, software tools, and project descriptions

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

 Azerb

-0.02

Þ

-0.02

oÄŁ

-0.02

elsius

-0.02

ĳå£«

-0.02

 guiActiveUn

-0.02

ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ

-0.01

ļéĨĴ

-0.01

ñ

-0.01

£ı

-0.01

POSITIVE LOGITS

↵

0.02

the

0.02

and

0.02

in

0.02

of

0.02

to

0.02

Activations Density 26.905%

technical information and data-related terms, like statistical measures, software tools, and project descriptions

No Comments

No Known Activations