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

DockStyle

-0.99

httphttps

-0.80

 doInBackground

-0.79

OGND

-0.75

 okuyayım

-0.73

providedIn

-0.72



-0.70

AccessorTable

-0.69

++.

-0.68

Portale

-0.68

POSITIVE LOGITS

 nahilalakip

0.47

 utafitiHapana

0.46

oredCriteria

0.46

 pinulongan

0.43

 '\\;'

0.38

 franceses

0.38

 morphe

0.38

 posteriores

0.36

 favorita

0.36

 hort

0.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.