INDEX

Explanations

words associated with stealth or secretive actions

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

hip

-1.58

poons

-1.53

 seat

-1.43

odi

-1.42

anya

-1.40

 head

-1.40

ione

-1.39

resa

-1.38

 stomach

-1.37

 myself

-1.35

POSITIVE LOGITS

¯

1.92

ĻĤ

1.68

¤

1.62

Ĵ

1.59

agogue

1.54

Īĺ

1.50

Ģ

1.50

ĺ

1.48

º

1.48

otypes

1.48

Activations Density 0.068%

words associated with stealth or secretive actions

No Comments

No Known Activations