INDEX

Explanations

references to chapters or sections in a document

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Monfieur

-0.74

 ujednoznacz

-0.68

 وتسجيلات

-0.65

wiſe

-0.59

Efq

-0.57

HostException

-0.57

 Shakspeare

-0.56

ilustrasi

-0.56

titud

-0.56

ividual

-0.56

POSITIVE LOGITS

 chapter

1.27

 chapters

1.26

 Chapter

1.17

chapters

1.09

Chapter

1.08

 Chapters

1.06

chapter

1.05

 CHAPTER

1.00

CHAPTER

0.99

Chapters

0.98

Activations Density 0.256%

references to chapters or sections in a document

No Comments

No Known Activations