INDEX

Explanations

references to episodes and their details in a television series

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

TV or film "episodes"

np_acts-logits-general · gemini-2.0-flash

episode or episodes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.63

 CreateTagHelper

-0.58

 CURIAM

-0.53

IsMutable

-0.49

unknownFields

-0.48

 kierow

-0.48

LLocation

-0.47

orsese

-0.45

ceptives

-0.45

saraba

-0.45

POSITIVE LOGITS

 episode

0.76

 episodes

0.75

 Episodes

0.59

 finale

0.57

 Episode

0.57

 episodio

0.54

episode

0.54

Episode

0.54

 chapter

0.52

pisode

0.51

Activations Density 0.152%

references to episodes and their details in a television series

TV or film "episodes"

episode or episodes

No Comments

No Known Activations