INDEX

Explanations

terms related to prime numbers and their factors

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

principalTable

-0.59

SourceChecksum

-0.56

Fordítás

-0.56

InputBorder

-0.50

setVerticalGroup

-0.50

CloseOperation

-0.50

FDRE

-0.48

ientras

-0.48

RTGC

-0.47

optionalTypeArgs

-0.47

POSITIVE LOGITS

AnimationsModule

0.46

MemoryWarning

0.40

 Administrativna

0.40

djangoproject

0.38

medriver

0.37

thumbsup

0.36

 thích

0.35

 mejora

0.35

 supplémentaires

0.35

 vectorielle

0.35

Activations Density 0.112%

terms related to prime numbers and their factors

prime factors

No Comments

No Known Activations