INDEX

Explanations

attends to location or attribute-related tokens from corresponding descriptive tokens

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

1:0.19

2:0.15

3:0.09

4:0.09

5:0.04

6:0.08

7:0.16

Negative Logits

 Italijanski

-0.28

#+#

-0.25

lunda

-0.25

RetentionPolicy

-0.25

olol

-0.24

 '\\;'

-0.24

IZONTAL

-0.23

omitempty

-0.23

 Bourgoin

-0.23

发表于

-0.22

POSITIVE LOGITS

Награды

0.29

 HasFactory

0.29

 Prizes

0.29

gezogen

0.27

 Boil

0.26

 gerekiyor

0.26

 beginnetje

0.26

 prêmio

0.25

matchCondition

0.25

 ionic

0.25

Activations Density 0.036%

attends to location or attribute-related tokens from corresponding descriptive tokens

No Comments

No Known Activations