INDEX

Explanations

patterns related to coding, algorithms, or technical documentation

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

Follows "Q:" or currency symbols

np_acts-logits-general · gemini-2.0-flash

Q: or later

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

Personendaten

-0.96

 ویکی‌پدی

-0.77

contentLoaded

-0.75

 متعلقه

-0.72

يكب

-0.71

 Himo

-0.68

__*/

-0.66

 StatefulWidget

-0.65

ItemBackground

-0.64

 AssemblyTitle

-0.63

POSITIVE LOGITS

uxxxx

0.65

 XCTest

0.47

<table>

0.47

Auszeichnungen

0.46

PickerController

0.45

 Growth

0.44

horesis

0.43

WebVitals

0.42

 dise

0.42

 Hospice

0.41

Activations Density 0.067%

patterns related to coding, algorithms, or technical documentation

Follows "Q:" or currency symbols

Q: or later

No Comments

No Known Activations