INDEX

Explanations

references to names or titles related to individuals or groups

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

AnchorStyles

-0.99

queryInterface

-0.97

WebVitals

-0.92

BagConstraints

-0.89

reportWebVitals

-0.86

GEBURTSDATUM

-0.83

 bezeichneter

-0.80

 utafitiHapana

-0.80

 مشين

-0.77

WindowConstants

-0.75

POSITIVE LOGITS

出版年

0.75

 nakalista

0.58

 Мексичка

0.56

 Sélectionnez

0.55

<bos>

0.51

thren

0.50

ništvo

0.47

jfree

0.46

cupertino

0.45

Geplaatst

0.44

Activations Density 4.191%

references to names or titles related to individuals or groups

No Comments

No Known Activations