INDEX

Explanations

numerical data and statistical results related to studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Hundreds

-0.60

Thousands

-0.58

 Thousands

-0.56

 adresa

-0.54

Fifty

-0.54

 tenth

-0.53

 fifteenth

-0.53

Sixty

-0.53

 Sixty

-0.52

 Eighty

-0.52

POSITIVE LOGITS

 three

0.72

 يتيمه

0.71

 four

0.70

 <<<<<<<<<<<<<<

0.70

Datuak

0.66

+#+#

0.64

four

0.59

>");

0.58

 الرخصة

0.56

 visibilité

0.56

Activations Density 0.309%

numerical data and statistical results related to studies

No Comments

No Known Activations