INDEX

Explanations

attends to instance-related tokens from corresponding tokens that refer to a quality or characteristic

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

0:0.11

1:0.12

2:0.13

3:0.08

4:0.04

5:0.01

6:0.08

7:0.38

Negative Logits

AndEndTag

-0.36

verwijspagina

-0.33

+#+#

-0.32

̍t

-0.27

Slf

-0.27

openConnection

-0.27

FormTagHelper

-0.26

TagMode

-0.25

ThroughAttribute

-0.25

MergeFrom

-0.24

POSITIVE LOGITS

XmlAccessType

0.31

 autorytatywna

0.28

 meille

0.27

 produisons

0.27

 thiệu

0.27

 gedaan

0.26

 profondità

0.26

othesis

0.26

ignty

0.25

vertisement

0.25

Activations Density 0.198%

attends to instance-related tokens from corresponding tokens that refer to a quality or characteristic

No Comments

No Known Activations