INDEX

Explanations

references to license agreements and usage permissions in software documentation

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

 impression

-1.59

¾

-1.52

Ń

-1.52

yne

-1.46

ı

-1.37

 plex

-1.36

 illusion

-1.30

edia

-1.29

atre

-1.29

 proportions

-1.26

POSITIVE LOGITS

 Unless

1.92

Unless

1.75

================================================================

1.71

unless

1.62

)?

1.53

________________________________

1.52

********************************

1.49

uckles

1.49

ureus

1.49

Case

1.48

Activations Density 0.042%

references to license agreements and usage permissions in software documentation

No Comments

No Known Activations