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

 team

-0.57

who

-0.48

 Team

-0.48

 officio

-0.46

 jure

-0.46

ghalaya

-0.44

 opération

-0.43

簿

-0.43

 masa

-0.42

amilya

-0.42

POSITIVE LOGITS

DeleteBehavior

0.85

 betweenstory

0.85

mybatisplus

0.85

yntaxException

0.85

Portail

0.79

"}")

0.79

ftagPool

0.78

WebVitals

0.78

 composers

0.77

Xna

0.75

Activations Density 0.020%

No Comments

No Known Activations