INDEX

Explanations

references to pages in academic works or publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 JpaRepository

-0.65

 Normdatei

-0.60

Datuak

-0.60

 compose

-0.58

::_('

-0.58

 OnInit

-0.56

 EventArgs

-0.56

unzel

-0.55

entai

-0.54

 برانيه

-0.54

POSITIVE LOGITS

 coûte

0.81

Stayed

0.78

ט

0.71

 costly

0.69

 coû

0.68

 spending

0.67

 spends

0.66

 expenditures

0.65

 Expenditure

0.63

 expenditure

0.60

Activations Density 0.176%

references to pages in academic works or publications

No Comments

No Known Activations