INDEX

Explanations

references to devices and their components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

 device

-2.77

 devices

-2.44

 Device

-2.41

device

-2.33

 Devices

-2.31

Device

-2.20

 DEVICE

-2.03

devices

-2.02

Devices

-1.94

 DEVICES

-1.74

POSITIVE LOGITS

esModule

0.54

 DriverManager

0.54

)))));

0.54

賀状

0.53

 userManager

0.52

}$.\\

0.52

Abitanti

0.50

writeField

0.50

 transfieras

0.49

 officielles

0.48

Activations Density 0.141%

references to devices and their components

No Comments

No Known Activations