INDEX

Explanations

chapter and section references in a text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.17.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

 AssemblyCulture

-0.83

 scale

-0.83

ंदीखरीदारी

-0.82

 CreateTagHelper

-0.81

 escala

-0.80

 Scale

-0.76

Sklici

-0.75

scale

-0.73

 SCALE

-0.72

 للاسماء

-0.68

POSITIVE LOGITS

 chapter

1.52

 Chapter

1.48

Chapter

1.42

CHAPTER

1.31

 chapters

1.27

chapter

1.24

 CHAPTER

1.19

 Kapitel

1.13

 Chapters

1.09

 chapitre

1.04

Activations Density 0.693%

chapter and section references in a text

No Comments

No Known Activations