INDEX

Explanations

words relevant to books, episodes

oai_token-act-pair · gemini-2.0-flash

chapter/episode

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 chapter

-1.76

 episode

-1.71

Chapter

-1.71

 Chapter

-1.71

 Episode

-1.53

chapter

-1.51

 capítulo

-1.38

Episode

-1.35

 chapters

-1.34

CHAPTER

-1.32

POSITIVE LOGITS

oredCriteria

0.89

 HasFactory

0.70

ftagPool

0.66

 Orrell

0.60

msgTypes

0.58

AndEndTag

0.57

CLUYE

0.57

-------

0.57

testen

0.56

 Wors

0.56

Activations Density 17.624%

words relevant to books, episodes

chapter/episode

No Comments

No Known Activations