INDEX

Explanations

attends to functions and commands from tokens related to case or legal terminology

oai_attention-head · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k

Configuration

google/gemma-scope-2b-pt-att/layer_10/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.10.attn.hook_z

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.17

1:0.09

2:0.17

3:0.05

4:0.05

5:0.05

6:0.05

7:0.35

Negative Logits

nor

-0.37

 StatefulWidget

-0.37

 StatelessWidget

-0.28

or

-0.28

WithTag

-0.26

bten

-0.26

 palla

-0.25

::*;

-0.25

/**

-0.25

 henvisninger

-0.25

POSITIVE LOGITS

astify

0.36

parsedMessage

0.35

ніципа

0.33

DrawerToggle

0.32

Personensuche

0.31

 centrifug

0.30

 betweenstory

0.29

 ostavi

0.29

 interchang

0.29

 unſ

0.28

Activations Density 0.001%

attends to functions and commands from tokens related to case or legal terminology

No Comments

No Known Activations