INDEX

Explanations

data structures or coding elements related to object addresses and peer information

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

Numbers within hexadecimal code or references

np_acts-logits-general · gemini-2.0-flash

contracted or contracts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

verwijspagina

-0.65

 OMIT

-0.58

 оригіналу

-0.58

 سكانية

-0.55

 архивлан

-0.55

ולוג

-0.53

StoreMessageInfo

-0.52

ఔ

-0.51

 ویکی‌پدیا

-0.51

QMetaType

-0.51

POSITIVE LOGITS

TestingModule

0.57

 roost

0.51

 contrats

0.51

<bos>

0.49

 contracted

0.48

WithMany

0.47

aA

0.47

zuma

0.46

mockito

0.46

ristor

0.45

Activations Density 0.100%

data structures or coding elements related to object addresses and peer information

Numbers within hexadecimal code or references

contracted or contracts

No Comments

No Known Activations