INDEX

Explanations

references to various types of elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ніципалі

-0.83

Personendaten

-0.68

verifyException

-0.67

sizeCache

-0.67

HasIndex

-0.66

BeginInit

-0.66

withIdentifier

-0.65

 AssemblyCulture

-0.64

 Extragalactic

-0.61

riedenheit

-0.61

POSITIVE LOGITS

 element

0.90

 elements

0.89

lement

0.75

 icon

0.64

 Element

0.63

 элемент

0.62

 Icon

0.62

 éléments

0.61

元素

0.58

 ELEMENTS

0.56

Activations Density 0.173%

references to various types of elements

No Comments

No Known Activations