INDEX

Explanations

attends to numerical indicators and specific edition or version tokens from subsequent references

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

0:0.13

1:0.23

2:0.15

3:0.08

4:0.08

5:0.03

6:0.05

7:0.20

Negative Logits

TestingModule

-0.29

ariam

-0.23

ʁ

-0.22

编

-0.21

 fram

-0.21

 inferior

-0.21

']==

-0.21

 Chau

-0.21

 Amor

-0.21

Flat

-0.21

POSITIVE LOGITS

يكب

0.46

+#+#

0.45

TRIBUN

0.39

expandindo

0.39

 متعلقه

0.37

 Italijani

0.35

 ostavi

0.34

Vidite

0.34

 LCCN

0.32

Rptr

0.31

Activations Density 0.148%

attends to numerical indicators and specific edition or version tokens from subsequent references

No Comments

No Known Activations