INDEX

Explanations

queries related to prime factorization

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

prime factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

}{@

-0.38

สำ

-0.37

croll

-0.35

amodel

-0.34

Rüyada

-0.31

 performed

-0.30

 numberOfRows

-0.30

 Jesús

-0.30

 completo

-0.29

ื่น

-0.29

POSITIVE LOGITS

úgó

0.59

raltar

0.54

 arşivlendi

0.54

ⓧ

0.52

 ब्रेकडाउन

0.49

typeorm

0.49

Ӕ

0.48

Хьажоргаш

0.48

 CanadaChoose

0.47

WriteTagHelper

0.45

Activations Density 0.157%

queries related to prime factorization

prime factors

No Comments

No Known Activations