INDEX

Explanations

references to convolution in the context of neural networks and image processing

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

convolution, CNNs, deconvolution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 voici

-0.48

 mismos

-0.43

providedIn

-0.40

AccessorTable

-0.39

 mismas

-0.39

 mesmas

-0.39

ambién

-0.38

endphp

-0.38

 mismo

-0.36

DataSnapshot

-0.36

POSITIVE LOGITS

 convolution

1.84

convolution

1.83

 Convolution

1.78

Convolution

1.69

 convolutional

1.53

卷

0.84

 Conv

0.80

 convoluted

0.79

卷

0.78

Conv

0.73

Activations Density 0.009%

references to convolution in the context of neural networks and image processing

convolution, CNNs, deconvolution

No Comments

No Known Activations