INDEX

Explanations

occurrences of the term "ene."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anic

-1.73

soever

-1.68

ty

-1.60

iginally

-1.57

")

-1.56

chy

-1.56

inny

-1.54

");

-1.52

rian

-1.51

lando

-1.48

POSITIVE LOGITS

loop

1.70

ĻĤ

1.69

hart

1.68

efs

1.62

 juror

1.54

 storytelling

1.54

 shots

1.50

wind

1.44

 excerpt

1.43

 Woods

1.42

Activations Density 0.041%

occurrences of the term "ene."

No Comments

No Known Activations