INDEX

Explanations

mathematical constructs or notations related to functions and operators

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

LaTeX math mode

np_acts-logits-general · gemini-2.0-flash

LaTeX math symbols

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

<eos>

-0.59

-0.42

-0.40

</blockquote>

-0.39

er

-0.39

↵↵

-0.38

 tiros

-0.36

POSITIVE LOGITS

脚注の使い方

1.05

 autorytatywna

1.02

 متعلقه

1.00

 nahilalakip

0.97

 referenties

0.97



0.95

Попис

0.93

 OFDb

0.92

 surla

0.91

EDEFAULT

0.87

Activations Density 1.473%

mathematical constructs or notations related to functions and operators

LaTeX math mode

LaTeX math symbols

No Comments

No Known Activations