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

InvalidProtocol

-1.02

oneofs

-0.79

 GenerationType

-0.76

 initComponents

-0.67

]").

-0.60

WriteTagHelper

-0.60

 ujednoznacz

-0.60

SourceChecksum

-0.57

dymyr

-0.56

argli

-0.55

POSITIVE LOGITS

visible

0.69

 visible

0.63

 GetEnumerator

0.62

 sicht

0.57

 Ababa

0.55

 visibles

0.55

 publicly

0.51

之外

0.50

 apparente

0.49

 Sequelize

0.48

Activations Density 0.162%

No Comments

No Known Activations