INDEX

Explanations

symbols and formatting related to data structures and API methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 estimés

-0.68

 intptr

-0.64

 ویکی‌پدیا

-0.62

fjspx

-0.59

Tikang

-0.57

 EconPapers

-0.56

例文帳に追加

-0.53

 الحره

-0.52

人民共和国

-0.51

pery

-0.51

POSITIVE LOGITS

aporation

0.60

 AssemblyCompany

0.59

 باسم

0.54

ftagPool

0.53

тельстве

0.53

@(

0.53

čenje

0.52

oporosis

0.51

 mids

0.50

berdayakan

0.50

Activations Density 0.357%

symbols and formatting related to data structures and API methods

No Comments

No Known Activations