INDEX

Explanations

technical terms related to neural network operations, particularly those involving convolutional and pooling layers

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

after "pool" or related to pooling

np_acts-logits-general · gemini-2.0-flash

pool, pooling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 Pritchard

-0.51

imet

-0.45

מד

-0.45

 Vectors

-0.45

Vectors

-0.43

 sportivo

-0.43

 BehaviorSubject

-0.42

ń

-0.42

ánto

-0.41

 jegy

-0.41

POSITIVE LOGITS

المناصب

0.83

 pooling

0.82

 pool

0.81

SequentialGroup

0.80

tagHelperRunner

0.77

pool

0.75

 Pool

0.73

Pool

0.72

RectangleBorder

0.71

Activations Density 0.193%

technical terms related to neural network operations, particularly those involving convolutional and pooling layers

after "pool" or related to pooling

pool, pooling

No Comments

No Known Activations