INDEX

Explanations

attends to time intervals marked in years from related tokens representing shorter time intervals

oai_attention-head · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k

Configuration

google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

0:0.01

1:0.04

2:0.08

3:0.13

4:0.10

5:0.07

6:0.27

7:0.26

Negative Logits

::_('

-0.45

ngdoc

-0.38

 ever

-0.35

̍t

-0.30

 VIAF

-0.28

Ligações

-0.26

ad

-0.25

men

-0.24

por

-0.24

POSITIVE LOGITS

isContained

0.60

ItemBackground

0.56

IUrlHelper

0.51

AddTagHelper

0.50

ValueStyle

0.50

esség

0.44

ImageContext

0.43

__);

0.43

reactstrap

0.43

ContentAsync

0.43

Activations Density 2.572%

attends to time intervals marked in years from related tokens representing shorter time intervals

No Comments

No Known Activations