INDEX

Explanations

names of researchers and their associated datasets 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 @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cencia

-0.74

 ProgressDialog

-0.72

 Seligman

-0.72

 voulu

-0.71

Marcia

-0.71

Portail

-0.71

Marne

-0.67

ăți

-0.67

 DEFIN

-0.67

/\.

-0.66

POSITIVE LOGITS

ollectionView

0.95

Personensuche

0.83

 Roja

0.82

 onCreateView

0.81

 Roskov

0.81

PropertyChanging

0.80

DS

0.79

 Avignon

0.79

 Wikimedijinoj

0.78

 Puch

0.78

Activations Density 1.152%

names of researchers and their associated datasets or publications

No Comments

No Known Activations