INDEX

Explanations

attends to programming terminology from code fragments that contain Java class definitions and annotations

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

0:0.09

1:0.13

2:0.10

3:0.13

4:0.14

5:0.09

6:0.15

7:0.13

Negative Logits

IContainer

-0.30

loroethene

-0.29

gdx

-0.28

sidenav

-0.28

erequisite

-0.28

helves

-0.27

hörige

-0.25

Ufficio

-0.24

ofür

-0.24

 ISNI

-0.24

POSITIVE LOGITS

 onAnimation

0.35

ⓧ

0.35

awaiter

0.33

;”

0.32

 propOrder

0.31

xchange

0.31

下载附件

0.29

+#+#

0.29

kapat

0.29

ImageContext

0.29

Activations Density 0.011%

attends to programming terminology from code fragments that contain Java class definitions and annotations

No Comments

No Known Activations