INDEX

Explanations

references to specific automotive parts or features, particularly related to new models and specifications

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

Numbers followed by units or brands

np_acts-logits-general · gemini-2.0-flash

numbers followed by units

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

complexContent

-0.72

 ویکی‌پدی

-0.70

neté

-0.69

Formats

-0.69

StoreMessageInfo

-0.66

PerformLayout

-0.66

ISupport

-0.65

 Pingback

-0.64

 typelib

-0.63

POSITIVE LOGITS

simov

0.41

اشته

0.39

 surla

0.39

เลย

0.39

ustimmung

0.37

 interior

0.37

beforeEach

0.37

 persoons

0.37

mobileqq

0.36

 newest

0.36

Activations Density 0.108%

references to specific automotive parts or features, particularly related to new models and specifications

Numbers followed by units or brands

numbers followed by units

No Comments

No Known Activations