INDEX

Explanations

terms related to feature selection 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

 disambiguazione

-0.53

 feroit

-0.52

 pleaſure

-0.48

carriage

-0.45

AutoresizingMask

-0.44

 ilmo

-0.44

 Numerade

-0.44

 arşivlendi

-0.44

Quiénes

-0.43

 HttpNotFound

-0.43

POSITIVE LOGITS

 methods

0.68

 method

0.65

 algorithms

0.64

 techniques

0.63

 algorithm

0.62

 algorit

0.56

 méthode

0.55

 methodology

0.54

 procedure

0.54

 methodologies

0.53

Activations Density 1.568%

terms related to feature selection methods in data processing

No Comments

No Known Activations