INDEX

Explanations

identifiers and numerical values related to data entries

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ffilmiau

-0.68

Tembelea

-0.64

PerformLayout

-0.64

UnitTesting

-0.63

tagHelperRunner

-0.63

})();

-0.61

ernalia

-0.61

 utafitiHapana

-0.61

 }}"></

-0.60

atically

-0.59

POSITIVE LOGITS

enumi

0.59

Abp

0.56

devtool

0.54

<bos>

0.53

glä

0.51

بوابة

0.51

 confronti

0.50

 елның

0.47

 Вікі

0.47

odd

0.47

Activations Density 0.081%

identifiers and numerical values related to data entries

No Comments

No Known Activations