INDEX

Explanations

elements and attributes related to programming structures and data organization

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

Code-related or class-related words

np_acts-logits-general · gemini-2.0-flash

code assignment or declaration

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

-0.70

-0.69

-0.68

-0.67

-0.65

-0.63

-0.62

-0.60

httphttps

-0.58

POSITIVE LOGITS

0.68

GraphicsUnit

0.66

ArrowToggle

0.54

 Wiktionnaire

0.52

 Cebuano

0.48

 Administrativna

0.47

 isInitialized

0.47

 Extragalactic

0.46

 Italijani

0.46

Autoritní

0.46

Activations Density 0.554%

elements and attributes related to programming structures and data organization

Code-related or class-related words

code assignment or declaration

No Comments

No Known Activations