INDEX

Explanations

specific options and settings within a software or application context

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

after settings/parameters/configurations

np_acts-logits-general · gemini-2.0-flash

tweaking configuration settings

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

KommentareTeilen

-0.83

BeginContext

-0.78

contentLoaded

-0.74

 مرئيه

-0.70

WithIOException

-0.69

isContained

-0.67

rungsseite

-0.60

invokeLater

-0.60

afficheront

-0.60

 onAnimation

-0.60

POSITIVE LOGITS

 settings

2.32

 Settings

1.91

settings

1.83

 setting

1.77

Settings

1.72

 SETTINGS

1.63

 Setting

1.56

Setting

1.47

setting

1.46

設定

1.46

Activations Density 0.757%

specific options and settings within a software or application context

after settings/parameters/configurations

tweaking configuration settings

No Comments

No Known Activations