INDEX

Explanations

medically relevant terminologies related to various procedures and conditions

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

»¿

-3.83

Īĺ

-3.74

ĥ

-3.58

ī

-3.45

¥

-3.45

Ŀ

-3.42

Ł

-3.35

Į

-3.33

§

-3.27

ı

-3.25

POSITIVE LOGITS

 Photograph

1.35

etting

1.33

Sox

1.32

keeping

1.31

ystems

1.30

ceral

1.30

manship

1.30

aptic

1.29

![**

1.29

virus

1.24

Activations Density 3.902%

medically relevant terminologies related to various procedures and conditions

No Comments

No Known Activations