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

EVER

-1.72

 strengths

-1.62

ia

-1.49

etus

-1.43

aden

-1.31

aptop

-1.30

 power

-1.30

frastructure

-1.30

GE

-1.30

acid

-1.29

POSITIVE LOGITS

bour

1.80

ttes

1.70

holders

1.63

 Protest

1.58

 remar

1.55

 marriages

1.54

shaw

1.53

 weddings

1.52

taient

1.42

spons

1.42

Activations Density 0.521%

instances of the word "it" in various contexts

No Comments

No Known Activations