INDEX

Explanations

references to series, books, and authors in textual content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 فريبيس

-0.56

ScopeManager

-0.49

addWidget

-0.48

seiti

-0.47

"]);

-0.46

UnitTesting

-0.46

 <=",

-0.44

ISupport

-0.44

ItemBackground

-0.44

rscheinlichkeit

-0.43

POSITIVE LOGITS

 series

3.07

series

2.67

 Series

2.35

 SERIES

2.30

Series

2.23

 série

2.18

 serie

2.17

SERIES

2.04

系列

2.01

シリーズ

1.96

Activations Density 0.339%

references to series, books, and authors in textual content

No Comments

No Known Activations