INDEX

Explanations

commands and advice related to maintaining or managing items, particularly in a technical or procedural context

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

preceding nouns or noun-like words in other languages

np_acts-logits-general · gemini-2.0-flash

how to make / create

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 CreateTagHelper

-0.87

 StatelessWidget

-0.84

der

-0.82

 nowhere

-0.77

Obrázky

-0.77

帖最后由

-0.72

RenderAtEndOf

-0.67

 بيها

-0.64

 الحره

-0.63

 مشين

-0.62

POSITIVE LOGITS

 את

1.03

 einen

0.76

den

0.74

einen

0.64

 diesen

0.62

 seinen

0.61

 jednu

0.58

 свою

0.58

 την

0.58

 swoją

0.57

Activations Density 0.031%

commands and advice related to maintaining or managing items, particularly in a technical or procedural context

preceding nouns or noun-like words in other languages

how to make / create

No Comments

No Known Activations