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

 Espec

-0.51

 overtime

-0.47

 arreglar

-0.45

 étoit

-0.45

simd

-0.44

 direta

-0.44

 sulphuric

-0.44

 rempliss

-0.43

elesaikan

-0.42

 logistique

-0.41

POSITIVE LOGITS

InjectAttribute

1.00

 الحره

0.87

ScopeManager

0.86

SpringBootTest

0.84

ViewFeatures

0.79

 nahilalakip

0.77

 незавершена

0.76

Tikang

0.74

expandindo

0.74

 resourceCulture

0.73

Activations Density 0.044%

No Comments

No Known Activations