INDEX

Explanations

HTML metadata and document structure elements

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

Code-related tokens and numbers

np_acts-logits-general · gemini-2.0-flash

charset following punctuation

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

IsMutable

-0.96

 utafitiHapana

-0.90

rrggbb

-0.87

IsContent

-0.87

 متعلقه

-0.85

تقاوى

-0.84

 myſelf

-0.83

RegressionTest

-0.81

:✨

-0.80

 ویکی‌پدیا

-0.80

POSITIVE LOGITS

 initial

0.57

EditorBrowsable

0.50

0.47

 лет

0.43

viewport

0.43

 Initial

0.43

ka

0.42

Initial

0.41

Activations Density 0.098%

HTML metadata and document structure elements

Code-related tokens and numbers

charset following punctuation

No Comments

No Known Activations