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

yntaxException

-0.53

tagHelperRunner

-0.51

CPI

-0.48

XtraEditors

-0.47

오

-0.46

 marcher

-0.46

PUC

-0.45

بيوتر

-0.44

Humor

-0.44

 USAGE

-0.44

POSITIVE LOGITS

 initiatives

0.87

 objectives

0.82

 goals

0.81

 initiative

0.70

 aims

0.70

 goal

0.69

 objectifs

0.69

uldron

0.68

 priorities

0.68

 agenda

0.68

Activations Density 0.055%

No Comments

No Known Activations