INDEX

Explanations

technical terms related to production and filmmaking

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

a TV show episode or chapter

np_acts-logits-general · gemini-2.0-flash

episode numbers or titles

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 للمعارف

-0.68

 Monfieur

-0.57

 Chriftian

-0.55

ſelves

-0.54

Derbyniad

-0.53

 scienza

-0.53

 unterkunft

-0.53

хьтан

-0.52

 Majefty

-0.52

 voordelen

-0.51

POSITIVE LOGITS

 episode

0.90

 chapter

0.72

 episodes

0.70

 Episode

0.60

episode

0.59

 Chapter

0.57

 episódio

0.57

 instalment

0.56

 capítulo

0.56

ep

0.55

Activations Density 0.253%

technical terms related to production and filmmaking

a TV show episode or chapter

episode numbers or titles

No Comments

No Known Activations