INDEX

Explanations

instances of the word "it" in various 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

 sorts

-1.65

ĵ

-1.48

...]

-1.48

ariate

-1.45

 yesterday

-1.44

ental

-1.42

...'

-1.37

selves

-1.35

..

-1.32

 area

-1.31

POSITIVE LOGITS

"</

1.69

\":

1.42

}</

1.42

ze

1.40

ħ

1.38

hov

1.38

bind

1.38

zn

1.37

itably

1.34

zes

1.34

Activations Density 0.401%

instances of the word "it" in various contexts

No Comments

No Known Activations