INDEX

Explanations

quantitative measurements or values

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

Timestamps appearing in subtitles

np_acts-logits-general · gemini-2.0-flash

numbers like 2.3, 2.4, 2.5

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Digitized

-0.53

Tembelea

-0.51

 ImGui

-0.50

Diweddarwch

-0.48

Hebrews

-0.47

WebElementEntity

-0.47

ACHUSET

-0.46

Второй

-0.45

Deux

-0.45

POSITIVE LOGITS

ftagPool

0.66

principalTable

0.63

جغرافيا

0.62

baugh

0.59

TagMode

0.58

RegressionTest

0.56

...@

0.56

SerializeField

0.56

")[

0.56

 Référence

0.56

Activations Density 0.268%

quantitative measurements or values

Timestamps appearing in subtitles

numbers like 2.3, 2.4, 2.5

No Comments

No Known Activations