INDEX

Explanations

technical terms and references related to scientific papers and processes

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

contentLoaded

-0.69

AnchorStyles

-0.61

出版年

-0.54

 tartalomajánló

-0.54

Aiheesta

-0.53

 externi

-0.53

EDEFAULT

-0.52

auteuil

-0.52

 AssemblyCompany

-0.51

 Democrá

-0.49

POSITIVE LOGITS

 للمعارف

0.58

 ModelExpression

0.57

onViewCreated

0.57

новниш

0.54

addPreferredGap

0.54

DotNetBar

0.54

 kolik

0.49

 متعلقه

0.49

üyor

0.49

LayoutStyle

0.47

Activations Density 0.652%

technical terms and references related to scientific papers and processes

No Comments

No Known Activations