INDEX

Explanations

mathematical notations and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

RegressionTest

-1.03

脚注の使い方

-0.88

)_/¯

-0.86

SharedCtor

-0.85

LookAnd

-0.85

 autorytatywna

-0.83

 initComponents

-0.78

NameInMap

-0.76

ⓧ

-0.71

 nahilalakip

-0.70

POSITIVE LOGITS

 fatica

0.56

 MainAxisSize

0.54

SerializedName

0.51

äher

0.50

makeConstraints

0.49

 BufferedImage

0.48

Revenir

0.47

 Ordnung

0.47

 cleanest

0.47

principalColumn

0.47

Activations Density 0.298%

mathematical notations and expressions

No Comments

No Known Activations