INDEX

Explanations

names and titles associated with artistic or cultural figures

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

使

-0.43

exp

-0.41

-0.40

-0.38

-0.37

 individuale

-0.36

sub

-0.36

el

-0.36

ex

-0.36

POSITIVE LOGITS

 nakalista

0.95

oredCriteria

0.91

 QWidget

0.90

 disambiguazione

0.88

 iconFacebook

0.85

Бахар

0.84

曖昧さ回避

0.79

 ostavi

0.78

 autorytatywna

0.78

homonymie

0.77

Activations Density 0.045%

names and titles associated with artistic or cultural figures

No Comments

No Known Activations