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

 Brito

-0.66

StrictEqual

-0.62

 Архивировано

-0.62

 DriverManager

-0.62

Perché

-0.61

mergeFrom

-0.59

意思

-0.58

scrollTop

-0.58

 consum

-0.58

-0.57

POSITIVE LOGITS

 notes

1.59

 note

1.54

 Notes

1.53

 NOTE

1.43

 Note

1.42

 Nota

1.34

 NOTES

1.34

notes

1.30

Note

1.30

note

1.28

Activations Density 0.051%

No Comments

No Known Activations