INDEX

Explanations

terms and concepts related to loss functions and optimization in machine learning

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

CNN, gradient, parameter, or learning

np_acts-logits-general · gemini-2.0-flash

gradient, optimizer, learning, CNN, cross-entropy

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 deck

-0.44

inde

-0.43

VEY

-0.42

ierungen

-0.42

verk

-0.42

жет

-0.41

 Brice

-0.41

jakan

-0.41

ニャ

-0.41

coln

-0.40

POSITIVE LOGITS

 optimizer

0.82

 learning

0.81

 препратки

0.80

optimizer

0.77

LookAnd

0.76

Personensuche

0.73

 Learning

0.73

Learning

0.72

learning

0.72

cheduler

0.71

Activations Density 0.484%

terms and concepts related to loss functions and optimization in machine learning

CNN, gradient, parameter, or learning

gradient, optimizer, learning, CNN, cross-entropy

No Comments

No Known Activations