INDEX

Explanations

instances of the term "act" or related variations

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

>`

-2.10

>';

-1.65

...'

-1.61

acetic

-1.56

omitempty

-1.52

ARC

-1.52

...?"

-1.51

>'

-1.48

've

-1.47

respectively

-1.47

POSITIVE LOGITS

ivities

1.93

uary

1.89

cule

1.88

ivism

1.75

icals

1.68

case

1.67

ivated

1.64

ism

1.62

ical

1.61

uelle

1.60

Activations Density 0.190%

instances of the term "act" or related variations

No Comments

No Known Activations