INDEX

Explanations

terms associated with medical diagnosis

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.0.hook_mlp_out

Hook Layer

Architecture

standard

Context Size

128

Dataset

EleutherAI/the_pile_deduplicated

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rap

-1.63

md

-1.56

ux

-1.54

join

-1.52

pcbi

-1.43

pped

-1.42

aned

-1.36

OL

-1.35

BIN

-1.33

rb

-1.29

POSITIVE LOGITS

itudes

1.75

¤

1.60

amente

1.50

ª

1.48

~~~

1.47

issance

1.47

»¿

1.46

WI

1.43

 amounts

1.43

alam

1.42

Activations Density 0.011%

terms associated with medical diagnosis

No Comments

No Known Activations