INDEX

Explanations

terms related to healthcare and medical products aimed at specific populations

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

£

-2.43

ĨĴ

-2.39

Į

-2.23

¯

-2.15

Ī

-2.10

ĥ½

-2.10

º

-2.05

«

-2.03

Ń

-2.01

¥

-2.00

POSITIVE LOGITS

 seasons

1.95

soever

1.93

 professions

1.91

 themselves

1.76

suits

1.63

 careers

1.59

unnumbered

1.59

 disciplines

1.52

 Athlet

1.52

thems

1.47

Activations Density 3.289%

terms related to healthcare and medical products aimed at specific populations

No Comments

No Known Activations