INDEX

Explanations

terminology related to immune cells and their functions

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

roelectric

-1.46

criptive

-1.44

bital

-1.39

hline

-1.39

TAB

-1.37

 grain

-1.31

 decir

-1.31

boldmath

-1.30

 hers

-1.30

rist

-1.29

POSITIVE LOGITS

ulose

1.78

 immunity

1.77

 counts

1.60

Ł

1.55

ault

1.53

 responded

1.44

 injury

1.40

 responds

1.39

 immunodeficiency

1.38

 lymphoma

1.36

Activations Density 0.076%

terminology related to immune cells and their functions

No Comments

No Known Activations