INDEX

Explanations

terms related to experimental data analysis and modeling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Numerade

-0.72

 PeEnEo

-0.57

enumii

-0.55

 surla

-0.52

 EconPapers

-0.51

 <<<<<<<<<<<<<<

-0.50

 disambiguazione

-0.49

 StatelessWidget

-0.47

AutoScaleMode

-0.47

POSITIVE LOGITS

 <>",

0.44

 fitting

0.39

vateľ

0.38

 Züge

0.38

 slope

0.37

 africains

0.36

 Gipfel

0.35

 graag

0.35

 Asien

0.35

sätzlich

0.35

Activations Density 1.646%

terms related to experimental data analysis and modeling

No Comments

No Known Activations