INDEX

Explanations

words related to health and medicine

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

boy

-1.45

uu

-1.30

ľĵ

-1.30

 missing

-1.30

cake

-1.28

 Assumption

-1.27

yet

-1.23

 still

-1.23

oh

-1.22

immun

-1.22

POSITIVE LOGITS

wikipedia

1.81

 ensued

1.52

 decades

1.50

 centuries

1.50

oretic

1.45

otom

1.45

StackTrace

1.42

ETHOD

1.41

 argument

1.33

cite

1.33

Activations Density 1.818%

words related to health and medicine

No Comments

No Known Activations