INDEX

Explanations

references to Java annotations

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

"annotation" or "annotations"

np_acts-logits-general · gemini-2.0-flash

annotation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ंदीखरीदारी

-0.79

انجليز

-0.76

 cherchés

-0.69

Portail

-0.64

 ihop

-0.64

webElementXpaths

-0.62

ChildScrollView

-0.61

 tár

-0.61

 conseguenza

-0.60

Datuak

-0.60

POSITIVE LOGITS

annotation

1.12

annotations

0.99

Annotations

0.78

 annotation

0.77

 anno

0.76

躇

0.75

Annotation

0.72

 Annotation

0.69

Anno

0.67

 annotations

0.67

Activations Density 0.032%

references to Java annotations

"annotation" or "annotations"

annotation

No Comments

No Known Activations