INDEX

Explanations

references to instructions or guides for configuration settings

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

https:// URLs

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

RenderAtEndOf

-0.59

InjectMocks

-0.54

 mxArray

-0.49

 impresiones

-0.47

jenige

-0.46

 propuesto

-0.45

 quizá

-0.44

сылкі

-0.44

にほんブログ村

-0.43

 feminina

-0.43

POSITIVE LOGITS

 Ratt

0.46

WillAppear

0.46

 Talon

0.43

RefNanny

0.42

 methodologies

0.40

TEM

0.40

Vidite

0.40

labus

0.40

DidLoad

0.39

 ratt

0.39

Activations Density 0.013%

references to instructions or guides for configuration settings

https:// URLs

No Comments

No Known Activations