INDEX

Explanations

numeric values and references related to scientific data

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

references and tables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

.*")]

-0.62

出版年

-0.52

bootstrapcdn

-0.52

 Forderung

-0.49

Награды

-0.41

 desselben

-0.39

>",

-0.39

yfikacja

-0.39

XmlAccessorType

-0.39

 tức

-0.39

POSITIVE LOGITS

bohemian

0.37

 Linear

0.37

onden

0.37

Predecesor

0.36

はじめに

0.36

 nahilalakip

0.36

angerie

0.36

addTab

0.35

runde

0.35

 Quantitative

0.35

Activations Density 0.016%

numeric values and references related to scientific data

references and tables

No Comments

No Known Activations