INDEX

Explanations

specific terminologies and concepts associated with legal or regulatory frameworks

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

standard

Context Size

128

Dataset

EleutherAI/the_pile_deduplicated

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ļª

-2.67

ĻĤ

-2.65

Ŀ

-2.40

Ľ

-2.36

ı

-2.34

¿½

-2.33

ŀ

-2.29

ľĵ

-2.29

£

-2.27

Ī

-2.24

POSITIVE LOGITS

anean

1.78

 lightly

1.63

fered

1.52

 excellence

1.41

antis

1.39

ely

1.38

actory

1.37

 manufacturers

1.32

 preponderance

1.32

 competition

1.32

Activations Density 1.060%

specific terminologies and concepts associated with legal or regulatory frameworks

No Comments

No Known Activations