INDEX

Explanations

the verb "be" in various forms and contexts

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

¢

-2.86

ī

-2.79

Ĺ

-2.67

Īĺ

-2.66

ĨĴ

-2.60

§

-2.59

¼

-2.58

ĺ

-2.56

Ģ

-2.56

Ķ

-2.54

POSITIVE LOGITS

vereign

1.60

rium

1.49

illance

1.47

 innocent

1.46

ness

1.42

vate

1.41

etal

1.40

lessness

1.40

 else

1.38

rike

1.38

Activations Density 0.329%

the verb "be" in various forms and contexts

No Comments

No Known Activations