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

 betweenstory

-1.23

Personendaten

-1.13

MessageOf

-1.04

ViewFeatures

-1.02

parsedMessage

-1.02

WithIOException

-1.02

sidemargin

-0.96

 '\\;'

-0.95

Vidite

-0.95

enterOuterAlt

-0.95

POSITIVE LOGITS

//

0.72

///<

0.66

/**

0.63

/*

0.52

It

0.50

 εν

0.50

<i>

0.50

 rowspan

0.49

.~\

0.49

 tham

0.49

Activations Density 0.001%

No Comments

No Known Activations