INDEX

Explanations

terms related to medical classifications and coding systems

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

ingly

-1.76

tered

-1.65

:`

-1.56

github

-1.52

[]{

-1.40

)](

-1.39

ificantly

-1.38

 cleanup

-1.38

ithub

-1.37

 downstream

-1.36

POSITIVE LOGITS

¸

2.59

ī

2.42

Ŀ

2.37

İ

2.29

ĳ

2.27

Ļª

2.23

ĩ

2.20

»¿

2.14

´

2.11

Ħ

2.09

Activations Density 1.125%

terms related to medical classifications and coding systems

No Comments

No Known Activations