INDEX

Explanations

abbreviations and codes related to locations and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ագրություններ

-0.55

UserScript

-0.53

DrawerToggle

-0.52

nader

-0.52

RefNanny

-0.51

jarah

-0.48

Ố

-0.46

 complexe

-0.45

eser

-0.45

cedures

-0.44

POSITIVE LOGITS

tagHelperRunner

0.81

AddTagHelper

0.78

Autoritní

0.72

 zijne

0.71

 Normdatei

0.66

NameInMap

0.65

 дописавши

0.64

 الاطلاع

0.61

 oprot

0.61

antaine

0.60

Activations Density 0.565%

abbreviations and codes related to locations and organizations

No Comments

No Known Activations