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

ApiModelProperty

-0.66

ärä

-0.63

fstream

-0.62

gsmål

-0.60

readFileSync

-0.60

guardo

-0.60

ález

-0.60

 DriverManager

-0.59

 estimés

-0.58

enzio

-0.56

POSITIVE LOGITS

 repeats

1.48

 Repeat

1.48

 Repe

1.47

 repetition

1.43

 repeat

1.42

 Repetition

1.39

 repeating

1.37

 repeater

1.36

Repeat

1.35

Repe

1.33

Activations Density 0.057%

No Comments

No Known Activations