INDEX

Explanations

structured data or code elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

UnusedPrivate

-0.72

LookAnd

-0.69

存于互联网档案馆

-0.60

 TestBed

-0.58

invokeLater

-0.57

AccessorTable

-0.56

EFIAPI

-0.56

keyColumn

-0.54

tagHelperRunner

-0.53

 Rptr

-0.53

POSITIVE LOGITS

 lenker

0.67

 viewDidLoad

0.60

 Holm

0.57

ньше

0.55

 royaume

0.54

 AppCompat

0.52

 appui

0.52

exels

0.51

 للمعارف

0.51

IZABETH

0.50

Activations Density 0.049%

structured data or code elements

No Comments

No Known Activations