INDEX

Explanations

code snippets related to function and variable definitions in programming

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

icum

-1.80

ize

-1.68

hibit

-1.67

...](

-1.65

 thereof

-1.64

omycin

-1.58

opsis

-1.58

bib

-1.57

atorium

-1.57

cellent

-1.57

POSITIVE LOGITS

¦

1.90

ī

1.61

Ī

1.54

ľĵ

1.54

£

1.53

 async

1.52

ķ

1.49

 foreach

1.44

Ĵ

1.43

def

1.43

Activations Density 0.413%

code snippets related to function and variable definitions in programming

No Comments

No Known Activations