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

AndEndTag

-0.79

ScopeManager

-0.71

—

-0.59

Pfalz

-0.57

patron

-0.55

awaiter

-0.55

脚注の使い方

-0.55

 Assistants

-0.55

Tikang

-0.54

specialchars

-0.54

POSITIVE LOGITS

 index

0.73

 indexes

0.67

 indices

0.65

 índice

0.64

 Índice

0.60

Indices

0.60

 Index

0.60

 linkovi

0.59

indices

0.58

icoot

0.57

Activations Density 0.049%

No Comments

No Known Activations