INDEX

Explanations

symbols and mathematical notations used in equations 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

 فريبيس

-0.71

 ContentValues

-0.60

 WaitForSeconds

-0.58

 étrangère

-0.56

 AppColors

-0.54

posedge

-0.52

Nol

-0.51

 agricoles

-0.50

 objectForKey

-0.50

flink

-0.50

POSITIVE LOGITS

})));

0.73

 kasarigan

0.71

 autorytatywna

0.68

 Wikimedijinoj

0.67

awtextra

0.65

();)

0.64

oredCriteria

0.62

✨:

0.62

horabuena

0.62

 ModelExpression

0.61

Activations Density 0.944%

symbols and mathematical notations used in equations and expressions

No Comments

No Known Activations