INDEX

Explanations

numerical data related to experimental results or statistical analysis

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

 للاسماء

-0.71

NameInMap

-0.70

AsUp

-0.68

 estekak

-0.62

CWE

-0.57

 utafitiHapana

-0.56

Cyfeiriadau

-0.56

">//

-0.55

хьтан

-0.55

 '\\;'

-0.54

POSITIVE LOGITS

 IBOutlet

0.77

SupportActionBar

0.76

providedIn

0.63

 viewDidLoad

0.62

 StatelessWidget

0.61

DropTable

0.61

Literatur

0.60

 дописавши

0.60

참고

0.58

 Pingback

0.58

Activations Density 0.123%

numerical data related to experimental results or statistical analysis

No Comments

No Known Activations