INDEX

Explanations

No Explanations Found

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

ricks

-1.70

Ã³g

-1.67

ching

-1.57

\[[@

-1.37

asti

-1.37

ter

-1.29

yne

-1.27

uffer

-1.25

 resolve

-1.25

ERC

-1.25

POSITIVE LOGITS

 Caption

1.65

iably

1.62

 himself

1.61

 caption

1.50

 footage

1.48

 biography

1.45

laughter

1.45

caption

1.43

ħ

1.40

 oneself

1.40

Activations Density 4.670%

No Known Activations

This feature has no known activations.