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

তথ্যসূত্র

-1.07

 betweenstory

-0.94

 autorytatywna

-0.92

saraba

-0.91

исленность

-0.90

脚注の使い方

-0.89

 متعلقه

-0.86

 Akismet

-0.85

الإنجليزية

-0.84

RegressionTest

-0.84

POSITIVE LOGITS

0.56

cru

0.49

<u>

0.47

0.44

CAL

0.44

<i>

0.44

 usual

0.44

<em>

0.42

gri

0.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.