INDEX

Explanations

mathematical notations and expressions related to variables and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ReusableCell

-0.77

 дописавши

-0.73

UrlResolution

-0.72

ErrorListener

-0.71

MigrationBuilder

-0.70

 bezeichneter

-0.69

Efq

-0.69

 jScrollPane

-0.68

 للاسماء

-0.68

RetentionPolicy

-0.65

POSITIVE LOGITS

XmlAccessorType

0.45

Демографія

0.42

<bos>

0.40

MathML

0.39

 gynhyrchwyd

0.39

nonatomic

0.38

de

0.37

 tổ

0.36

ciales

0.36

MemoryWarning

0.36

Activations Density 0.841%

mathematical notations and expressions related to variables and functions

No Comments

No Known Activations