INDEX

Explanations

references to settings and configurations in a technical context

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

configuration and settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

complexContent

-0.68

 utafitiHapana

-0.65

DoubleQuotes

-0.63

onAttach

-0.62

 Мексичка

-0.59

readAs

-0.59

contentLoaded

-0.57

GOTREF

-0.56

下载附件

-0.56

 JpaRepository

-0.55

POSITIVE LOGITS

 settings

0.62

 parameters

0.51

SETTINGS

0.50

 Settings

0.49

ariConfig

0.49

settings

0.49

 setting

0.48

ServletConfig

0.47

 Perſ

0.47

Settings

0.46

Activations Density 0.052%

references to settings and configurations in a technical context

configuration and settings

No Comments

No Known Activations