INDEX

Explanations

components of mathematical expressions, formulas, and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.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

tagHelperRunner

-0.86

 disambiguazione

-0.68



-0.56

IsMutable

-0.53

 iconLine

-0.52

SourceChecksum

-0.52

tvguidetime

-0.51

RegressionTest

-0.50

TypedDataSet

-0.50

endregion

-0.48

POSITIVE LOGITS

ไง

0.45

 pungkas

0.43

 veckor

0.41

 pungkasnya

0.40

Véxase

0.39

 baskılı

0.37

scry

0.37

 abbildung

0.37

GETHER

0.36

OGND

0.36

Activations Density 0.682%

components of mathematical expressions, formulas, and equations

No Comments

No Known Activations