INDEX

Explanations

attends to tokens indicating visibility from tokens indicating location or condition

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.61

1:0.02

2:0.02

3:0.02

4:0.20

5:0.03

6:0.01

7:0.05

Negative Logits

 кӀ

-0.29

Vidite

-0.28

 little

-0.25

room

-0.25

 maestra

-0.25

Allowed

-0.25

racite

-0.25

 picioare

-0.25

 lẽ

-0.24

POSITIVE LOGITS

 nonatomic

0.42

 StatefulWidget

0.41

存于互联网档案馆

0.40

 مشين

0.39

VIAF

0.39

 LoggerFactory

0.38

 onCreateView

0.38

 FetchType

0.37

 doInBackground

0.37

ModelSerializer

0.36

Activations Density 0.020%

attends to tokens indicating visibility from tokens indicating location or condition

No Comments

No Known Activations