INDEX

Explanations

measurements or data represented in a structured format, often related to statistical analysis

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

Text after section headings

np_acts-logits-general · gemini-2.0-flash

ARISING

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

RenderAtEndOf

-0.92

OGND

-0.91

 NUKAT

-0.86

المشاركات

-0.81

AsUp

-0.81

sizeCache

-0.79

Obrázky

-0.79

 ostavi

-0.79

########.

-0.77

WriteBarrier

-0.72

POSITIVE LOGITS

0.58

DeviceType

0.43

 humanas

0.43

newInstance

0.41

 parola

0.40

aság

0.40

Errors

0.40

vereins

0.39

 raso

0.39

 المعيارى

0.39

Activations Density 0.054%

measurements or data represented in a structured format, often related to statistical analysis

Text after section headings

ARISING

No Comments

No Known Activations