INDEX

Explanations

references to specific measurements and quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 Marín

-0.41

at

-0.40

in

-0.40

 Ahnung

-0.40

 based

-0.38

min

-0.37

junit

-0.36

<h1>

-0.35

 Pardo

-0.35

 Gómez

-0.34

POSITIVE LOGITS

 HasFactory

0.71

 Influencer

0.69

WebElementEntity

0.68

 surla

0.68

 transducer

0.68

 transducers

0.68

IsMutable

0.67

ruiter

0.67

ValueStyle

0.67

 Giuli

0.65

Activations Density 1.099%

references to specific measurements and quantities

No Comments

No Known Activations