INDEX

Explanations

commentary or documentation in code

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

// comment markers

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

BeginInit

-0.41

日起

-0.41

 surface

-0.40

}],

-0.40

"]();

-0.39

();)

-0.39

出版年

-0.39

 виправивши

-0.38

OGND

-0.37

ỡi

-0.36

POSITIVE LOGITS

 FetchType

0.46

帖最后由

0.46

aspectj

0.44

PYX

0.43

tagHelperRunner

0.43

 Италијани

0.42

 kasarigan

0.40

huahua

0.40

Tembelea

0.40

 gdyby

0.39

Activations Density 0.013%

commentary or documentation in code

// comment markers

No Comments

No Known Activations