INDEX

Explanations

attends to decade-related tokens marked by years from the connecting dash 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

0:0.08

1:0.11

2:0.09

3:0.10

4:0.10

5:0.08

6:0.19

7:0.20

Negative Logits

Referencias

-0.22

chtete

-0.21

rah

-0.21

 lenker

-0.21

tanleria

-0.20

仰

-0.20

/><

-0.20

ispiel

-0.19

jillo

-0.19

krivning

-0.19

POSITIVE LOGITS

 ainfi

0.40

Personensuche

0.39

 defStyle

0.38

 enfans

0.37

 estimés

0.37

MemoryWarning

0.36

 étoit

0.35

Portale

0.35

BrowserModule

0.35

 inconnu

0.35

Activations Density 0.008%

attends to decade-related tokens marked by years from the connecting dash tokens

No Comments

No Known Activations