INDEX

Explanations

code and library references related to image processing

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

↵↵

-0.45

-0.33

-0.29

-0.28

to

-0.25

-0.24

en

-0.24

POSITIVE LOGITS

GEBURTSDATUM

1.32

 ModelExpression

1.29

iſchen

1.28

<unused8>

1.27

<unused52>

1.27

[@BOS@]

1.27

<unused16>

1.27

<unused80>

1.27

<pad>

1.26

<unused1>

1.26

Activations Density 6.003%

code and library references related to image processing

No Comments

No Known Activations