INDEX

Explanations

elements related to episodic structure and narrative progression in television series

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

episodes, parts, or chapters

np_acts-logits-general · gemini-2.0-flash

parts of episodes and chapters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 mathvariant

-0.46



-0.45

FontOfSize

-0.43

 دیکھیے

-0.42

ngOnDestroy

-0.42

ervative

-0.41

 creatinine

-0.41

цездатний

-0.40

这项

-0.39

 Pyrénées

-0.39

POSITIVE LOGITS

 episode

1.61

 episodes

1.50

episode

1.32

 chapter

1.31

 chapters

1.29

 Episode

1.25

Episode

1.24

 Episodes

1.21

 instalment

1.19

 installment

1.17

Activations Density 0.271%

elements related to episodic structure and narrative progression in television series

episodes, parts, or chapters

parts of episodes and chapters

No Comments

No Known Activations