INDEX

Explanations

keywords related to non-profit organizations

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/1-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.1.hook_resid_post

Hook Layer

Architecture

standard

Context Size

128

Dataset

EleutherAI/the_pile_deduplicated

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ļª

-2.23

ĥ½

-1.83

¥

-1.75

ocardi

-1.74

ĨĴ

-1.69

ª

-1.61

ear

-1.55

Ĥ

-1.52

 mornings

-1.48

ĻĤ

-1.47

POSITIVE LOGITS

ceed

1.88

ceedings

1.85

posal

1.83

blems

1.72

gressive

1.65

clamation

1.64

hibition

1.60

ceeded

1.58

ceeding

1.58

claim

1.56

Activations Density 0.034%

keywords related to non-profit organizations

No Comments

No Known Activations