INDEX

Explanations

technical terms and coding syntax related to programming functions and definitions

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/4-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.4.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

 consisted

-1.66

 included

-1.49

 meant

-1.47

emed

-1.47

urity

-1.45

amino

-1.42

 aspect

-1.42

hors

-1.41

 aspects

-1.39

anas

-1.39

POSITIVE LOGITS

 delete

2.58

 dispose

2.53

 kill

2.49

 destroy

2.46

 write

2.43

 listen

2.42

 modify

2.40

 commit

2.39

 migrate

2.39

 consume

2.38

Activations Density 1.882%

technical terms and coding syntax related to programming functions and definitions

No Comments

No Known Activations