INDEX

Explanations

references to chapters in texts or documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

consulté

-0.72

ose

-0.67

 kling

-0.61

öt

-0.60

 Zool

-0.58

Кре

-0.58

 estimat

-0.57

мали

-0.57

zło

-0.57

ánt

-0.57

POSITIVE LOGITS

 chapter

2.26

 chapters

2.20

 Chapter

2.12

Chapter

2.06

 Chapters

2.05

CHAPTER

2.01

 CHAPTER

1.98

chapters

1.97

chapter

1.96

Chapters

1.86

Activations Density 0.130%

references to chapters in texts or documents

No Comments

No Known Activations