INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 dias

-0.61

-0.60

-0.56

out

-0.56

 Waldo

-0.54

erape

-0.53

 Recherches

-0.52

 الم

-0.51

cstring

-0.51

POSITIVE LOGITS

 governors

1.65

 Governors

1.59

 governor

1.43

 Governor

1.39

 GOVERN

1.38

 GOVERNOR

1.34

Govern

1.34

GOVERN

1.33

Governor

1.30

governor

1.27

Activations Density 0.013%

No Comments

No Known Activations