INDEX

Explanations

technical terms related to classification methods in data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

 للمعارف

-0.48

findpost

-0.44

 emailAlready

-0.41

EDEFAULT

-0.41

GEBURTS

-0.39

了一個

-0.38

 intptr

-0.37

 geboten

-0.36

Bisous

-0.36

 möjligt

-0.35

POSITIVE LOGITS

 classifications

0.59

 Types

0.54

 Classification

0.52

 IBOutlet

0.50

AndroidJUnit

0.49

 classification

0.48

 classifying

0.46

Classification

0.45

typen

0.45

 types

0.44

Activations Density 0.670%

technical terms related to classification methods in data processing

No Comments

No Known Activations