INDEX

Explanations

programming and dependency injection-related terms and annotations

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

programming keywords and annotations

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

 الحره

-0.62

 мәкал

-0.58

 تضيفلها

-0.57

abestanden

-0.54

AutoScaleMode

-0.51

󠁣

-0.50

stdafx

-0.50

 مواليد

-0.48

 BoxFit

-0.48

 ravis

-0.47

POSITIVE LOGITS

MockBean

0.99

InjectMocks

0.88

Autowired

0.80

FXML

0.69

ThroughAttribute

0.56

 useContext

0.54

FindBy

0.54

BindView

0.52

 CreateTagHelper

0.50

 useRef

0.49

Activations Density 0.001%

programming and dependency injection-related terms and annotations

programming keywords and annotations

No Comments

No Known Activations