INDEX

Explanations

queries related to prime factorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 Référence

-0.48

 invokingState

-0.46

MENAFN

-0.46

 tran

-0.44

FloatField

-0.44

 recue

-0.41

gra

-0.41

MergeFrom

-0.41

추

-0.40

ervo

-0.40

POSITIVE LOGITS

LookAnd

0.91

 primes

0.88

 Italijani

0.80

Primes

0.79

ьаж

0.78

 GenerationType

0.78

 prime

0.77

RenderAtEndOf

0.76

AndEndTag

0.75

primes

0.72

Activations Density 1.835%

queries related to prime factorization

No Comments

No Known Activations