INDEX

Explanations

terms related to the immune system and immune responses

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

hots

-1.75

ables

-1.66

lla

-1.64

orrow

-1.61

aliana

-1.54

else

-1.51

afers

-1.47

ateur

-1.46

owing

-1.46

als

-1.46

POSITIVE LOGITS

 microenvironment

1.64

 differently

1.64

 system

1.54

 compartment

1.54

 responses

1.50

 defenses

1.48

 response

1.46

 checkpoint

1.43

 clearance

1.41

 mediated

1.39

Activations Density 0.045%

terms related to the immune system and immune responses

No Comments

No Known Activations