INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

毛

-0.50

毛

-0.46

 Burgh

-0.44

thu

-0.44

cu

-0.44

Nav

-0.43

blan

-0.43

geh

-0.43

ch

-0.43

sca

-0.43

POSITIVE LOGITS

InjectAttribute

1.02

thâu

0.85

 GenerationType

0.82

reportWebVitals

0.78

 tartalomajánló

0.76

TintMode

0.74

ChromeDriver

0.74

 resourceCulture

0.73

 Audiodateien

0.73

MLLoader

0.73

Activations Density 0.000%

No Known Activations

This feature has no known activations.