INDEX

Explanations

references to official protocols, grants, and funding information related to scientific research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للمعارف

-0.71

 onPostExecute

-0.62

IsPostBack

-0.60

 mapStateToProps

-0.60

 AutoMapper

-0.58

NUMX

-0.56

SizeF

-0.52

Hozzáférés

-0.51

beforeAll

-0.49

WaitGroup

-0.49

POSITIVE LOGITS

BeginContext

0.88

0.85

 kasarigan

0.85

 number

0.81

$\#

0.80

\#

0.80

number

0.79

0.78

#:

0.77

 Number

0.75

Activations Density 1.273%

references to official protocols, grants, and funding information related to scientific research

No Comments

No Known Activations