INDEX

Explanations

terms related to handwritten digit recognition in machine learning contexts

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

12 Angry Men

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

ViewImports

-0.53

transQ

-0.48

 препратки

-0.46

 Autorizaciones

-0.43

 Kershaw

-0.42

ValueStyle

-0.42

 CreateTagHelper

-0.41

SerializeField

-0.41

 intptr

-0.41

AccessorTable

-0.40

POSITIVE LOGITS

ollectionView

0.40

 ſever

0.39

 viſ

0.38

 rhestr

0.38

mnist

0.37

InvalidProtocol

0.36

<%=

0.36

@[+][

0.36

 XNUMX

0.35

 nanot

0.35

Activations Density 0.003%

terms related to handwritten digit recognition in machine learning contexts

12 Angry Men

No Comments

No Known Activations