INDEX

Explanations

mathematical symbols and expressions related to equations

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

mathematical variables

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

 AssemblyTitle

-0.61

RenderAtEndOf

-0.59

 intptr

-0.56

 Waray

-0.54

ThroughAttribute

-0.53

 TestBed

-0.52

 AssemblyProduct

-0.49

󠁿

-0.49

 Thin

-0.48

AsUp

-0.48

POSITIVE LOGITS

下载附件

0.43

プローチ

0.39

Autor

0.35

 ilma

0.34

Witam

0.32

ién

0.32

 vallée

0.32

 entrevist

0.31

Arbeit

0.31

耘

0.31

Activations Density 0.300%

mathematical symbols and expressions related to equations

mathematical variables

No Comments

No Known Activations