INDEX

Explanations

technical terms and concepts related to image processing and neural networks

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

CNN filter, pooling, or kernel operations

np_acts-logits-general · gemini-2.0-flash

Gaussian filter parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 typelib

-0.56

 propOrder

-0.56

WebElementEntity

-0.55

 Prie

-0.51

 Disney

-0.50

 Tangerang

-0.50

 clientId

-0.50

 Bogen

-0.50

reportWebVitals

-0.49

 Lamar

-0.49

POSITIVE LOGITS

 kernel

0.81

 padding

0.77

kernel

0.75

Kernel

0.69

padding

0.69

 Kernel

0.62

pads

0.61

stride

0.61

 Padding

0.61

 stride

0.59

Activations Density 0.179%

technical terms and concepts related to image processing and neural networks

CNN filter, pooling, or kernel operations

Gaussian filter parameters

No Comments

No Known Activations