INDEX

Explanations

attends to the first token marked with double asterisks from the second token marked with double square brackets in a programming context

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

0:0.19

1:0.13

2:0.15

3:0.05

4:0.03

5:0.04

6:0.04

7:0.32

Negative Logits

///</

-0.33

ustris

-0.32

 informée

-0.31

TemporalType

-0.31

aarrggbb

-0.30

лян

-0.30

umur

-0.29

énario

-0.29

umy

-0.29

uegos

-0.28

POSITIVE LOGITS

 noqa

0.30

mybatisplus

0.29

stino

0.28

allos

0.27

 Njema

0.26

appid

0.26

Chham

0.25

beqa

0.25

CPD

0.24

antaranya

0.24

Activations Density 0.027%

attends to the first token marked with double asterisks from the second token marked with double square brackets in a programming context

No Comments

No Known Activations

attends to the first token marked with double asterisks from the second token marked with double square brackets in a programming context

No Comments

No Known Activations