INDEX

Explanations

concepts related to machine learning filtering techniques and their performance

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

IntoConstraints

-0.50

ftagPool

-0.47

OrNil

-0.46

/*

-0.40

//

-0.40

/**

-0.39

municipi

-0.39

execSQL

-0.38

}')

-0.38

splan

-0.36

POSITIVE LOGITS

 TestBed

0.46

 dummy

0.45

openConnection

0.42

RTHOOK

0.41

 Dummy

0.40

ंदीखरीदारी

0.38

Dummy

0.38

TextWatcher

0.38

tagext

0.38

dummy

0.37

Activations Density 0.679%

concepts related to machine learning filtering techniques and their performance

No Comments

No Known Activations