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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 herself

-1.68

 Stats

-1.47

 routine

-1.42

 foreseeable

-1.38

sie

-1.38

 Associates

-1.37

Mae

-1.35

 Siem

-1.34

 entangled

-1.33

 Manning

-1.33

POSITIVE LOGITS

»¿

2.09

ı

2.04

±

2.03

¶

2.00

ľĵ

1.96

¢

1.96

Į

1.90

ĳ

1.88

³

1.87

Ļª

1.83

Activations Density 1.625%

No Known Activations

This feature has no known activations.