INDEX

Explanations

technical terms and actions related to data manipulation and indexing

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

 Мексичка

-1.13

ⓧ

-0.71

LookAnd

-0.67

省市镇

-0.58

ChromeDriver

-0.55

 ComVisible

-0.55

 تضيفلها

-0.55

AppMethodBeat

-0.55

 protoimpl

-0.54

 Савезне

-0.53

POSITIVE LOGITS

 surla

0.65

 calendriers

0.63

 recommandée

0.57

MessageTagHelper

0.54

AddTagHelper

0.53

 onPostExecute

0.51

IsMutable

0.50

ReusableCell

0.50

AntiForgeryToken

0.49

 assurent

0.46

Activations Density 24.517%

technical terms and actions related to data manipulation and indexing

No Comments

No Known Activations