INDEX

Explanations

references to academic papers and related metadata

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

References or links with numbers and symbols

np_acts-logits-general · gemini-2.0-flash

patent citations and 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

зе

-0.54

multer

-0.52

Bibliografia

-0.47

 near

-0.45

 Dream

-0.45

 line

-0.44

Linki

-0.43

 lands

-0.43

bili

-0.43

line

-0.41

POSITIVE LOGITS

KommentareTeilen

1.02

AutoField

0.86

__":

0.83

 Roskov

0.77

 ExecuteAsync

0.72

Демографія

0.70

دانشنامهٔ

0.70

Diweddarwch

0.69

CloseOperation

0.68

Rüyada

0.67

Activations Density 0.151%

references to academic papers and related metadata

References or links with numbers and symbols

patent citations and abbreviations

No Comments

No Known Activations