INDEX

Explanations

keywords related to networking and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

webElementXpaths

-0.72

 autorytatywna

-0.61

-------------</

-0.58

 odkazy

-0.56

UseVisualStyle

-0.55

CDCl

-0.54

!*\

-0.52

SourceChecksum

-0.52

AsUp

-0.52

Controllo

-0.51

POSITIVE LOGITS

 المعيارى

0.76

ValueStyle

0.75

 BoxDecoration

0.68

 InputDecoration

0.63

 GenerationType

0.60

kranz

0.56

KURZBESCHREIBUNG

0.54

 contd

0.53

 JUGA

0.53

قایناقلار

0.53

Activations Density 0.164%

keywords related to networking and data structures

No Comments

No Known Activations