INDEX

Explanations

phrases related to functionality and usability in spaces and setups

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

 saites

-0.79

ScopeManager

-0.56

\|_{

-0.54

 faltar

-0.54

 AssemblyProduct

-0.53

 censiti

-0.51

 Smarty

-0.50

basicConfig

-0.49

ntlet

-0.48

 autorytatywna

-0.48

POSITIVE LOGITS

 storing

0.78

 Storing

0.68

 meetings

0.66

 storage

0.66

 overflow

0.65

 visitors

0.64

minaire

0.64

setViewportView

0.63

 comfortably

0.62

 Здесь

0.61

Activations Density 0.212%

phrases related to functionality and usability in spaces and setups

No Comments

No Known Activations