INDEX

Explanations

attends to tokens that feature arithmetic operations or relations on both sides

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

0:0.13

1:0.12

2:0.11

3:0.08

4:0.05

5:0.05

6:0.05

7:0.37

Negative Logits

AddTagHelper

-0.41

AndEndTag

-0.36

 '\\;'

-0.35

 OFDb

-0.33

PreferredItem

-0.29

 beginnetje

-0.29

corazón

-0.29

〢

-0.29

();)

-0.28

 AppCompatTheme

-0.28

POSITIVE LOGITS

出版年

0.26

putnik

0.26

maxcdn

0.25

чайно

0.25

дий

0.25

atoma

0.24

 görüş

0.24

JoinTable

0.24

displayquote

0.24

Activations Density 0.696%

attends to tokens that feature arithmetic operations or relations on both sides

No Comments

No Known Activations