INDEX

Explanations

instances of the word "Up"

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

Ĺ

-2.78

ĥ½

-2.62

·¸

-2.18

Ń

-2.14

Īĺ

-2.13

¼

-1.97

ĸ´

-1.92

¯

-1.90

ĺ

-1.82

©

-1.78

POSITIVE LOGITS

grade

1.98

dating

1.85

dates

1.69

hill

1.68

graded

1.65

"}](#

1.62

minster

1.60

ÅĽci

1.49

 Rapids

1.47

buntu

1.47

Activations Density 0.015%

instances of the word "Up"

No Comments

No Known Activations