INDEX

Explanations

terms related to feature selection and evolutionary algorithms 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 @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 المعيارى

-0.41

Hochspringen

-0.41

 تعدى

-0.37

 discul

-0.35

 Fälle

-0.35

发的

-0.35

 ब्रेकडाउन

-0.35

发了

-0.34

seteq

-0.34

 Worte

-0.34

POSITIVE LOGITS

 Plated

0.51

addPreferredGap

0.47

 Altern

0.46

 Swarm

0.46

 wireType

0.45

 createSprite

0.45

jaros

0.44

liders

0.44

 Endurance

0.43

WebServlet

0.43

Activations Density 0.902%

terms related to feature selection and evolutionary algorithms in data processing

No Comments

No Known Activations