INDEX

Explanations

references to scientific studies and their findings

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

Numbers and percentages

np_acts-logits-general · gemini-2.0-flash

numbers with units or abbreviations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

 Drapeau

-0.77

UnitTesting

-0.66

 يتيمه

-0.63

 noDo

-0.61

 autorytatywna

-0.58

/*

-0.57

 ویکی‌پدیای

-0.57

 onPostExecute

-0.57

esModule

-0.57

 intptr

-0.56

POSITIVE LOGITS

%</

0.57

"]];

0.54

jíma

0.49

ñora

0.49

 مشين

0.49

?");

0.49

üyada

0.49

]";

0.47

--;

0.46

estero

0.46

Activations Density 0.293%

references to scientific studies and their findings

Numbers and percentages

numbers with units or abbreviations

No Comments

No Known Activations