INDEX

Explanations

abbreviations or acronyms commonly used in scientific or technical contexts

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

ending in "m" or "sm"

np_acts-logits-general · gemini-2.0-flash

antivirals or muscular system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

aff

-0.66

MLLoader

-0.59

-0.58

外部リンク

-0.54

able

-0.53

aya

-0.52

unmodifiable

-0.51

openConnection

-0.51

setStroke

-0.50

이터

-0.49

POSITIVE LOGITS

 المعيارى

0.66

httphttps

0.64

Bm

0.64

 الرياضيه

0.63

 parseFrom

0.63

 архивлан

0.63

 Meksiku

0.62

jspx

0.60

 ViewModel

0.59

belec

0.59

Activations Density 0.417%

abbreviations or acronyms commonly used in scientific or technical contexts

ending in "m" or "sm"

antivirals or muscular system

No Comments

No Known Activations