INDEX

Explanations

mathematical terms and concepts related to evolutionary algorithms and feature selection

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

genotypic state

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

 ισ

-0.46

Sph

-0.46

 ति

-0.43

̀ng

-0.43

sat

-0.43

 bullet

-0.43

sit

-0.42

 sits

-0.42

тиво

-0.41

 wasser

-0.41

POSITIVE LOGITS



0.85

 genetic

0.81

 Genetic

0.79

EndProject

0.76

 chromosomes

0.75

ArrowToggle

0.73

 chromosome

0.72

 evolutionary

0.71

 genotype

0.71

Genetic

0.71

Activations Density 0.063%

mathematical terms and concepts related to evolutionary algorithms and feature selection

genotypic state

No Comments

No Known Activations