INDEX

Explanations

references to scientific publications or citations

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

places

-1.62

mes

-1.50

oz

-1.49

upp

-1.49

hip

-1.47

-1.41

arity

-1.41

 however

-1.39

$(

-1.39

?”

-1.37

POSITIVE LOGITS

ĨĴ

1.82

uthan

1.54

teenth

1.45

orge

1.39

 passage

1.34

doibase

1.31

ÏģÎ¯

1.30

fileID

1.30

quito

1.26

 attic

1.25

Activations Density 0.082%

references to scientific publications or citations

No Comments

No Known Activations