INDEX

Explanations

terms related to energy efficiency and performance metrics in technology or scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

大型

-0.43

fin

-0.42

 posiblemente

-0.42

 possibly

-0.42

 ruido

-0.41

 headed

-0.41

ண்ட

-0.41

④

-0.41

nościo

-0.41

 sớm

-0.40

POSITIVE LOGITS

 MainAxisSize

0.98

mybatisplus

0.86

 utafitiHapana

0.83

 BoxFit

0.81

 estekak

0.79

interopRequire

0.79

 surla

0.78

 MatDialog

0.77

 average

0.77

AddHtmlAttribute

0.77

Activations Density 1.477%

terms related to energy efficiency and performance metrics in technology or scientific contexts

No Comments

No Known Activations