INDEX

Explanations

attends to the closing braces of various namespaces from the opening namespace 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

0:0.11

1:0.14

2:0.12

3:0.11

4:0.12

5:0.08

6:0.14

7:0.16

Negative Logits

!';

-0.32

новништво

-0.30

[{\

-0.29

...');

-0.29

[-\

-0.29

ilarang

-0.29

<!--[

-0.28

WriteBarrier

-0.28

;->

-0.28

jusqu

-0.27

POSITIVE LOGITS

 Drapeau

0.32

帖最后由

0.31

 خارجية

0.31

 متعلقه

0.31

ReusableCell

0.28

 Jolla

0.27

enumi

0.26

PRNewswire

0.26

 تانيه

0.25

tvguidetime

0.25

Activations Density 0.002%

attends to the closing braces of various namespaces from the opening namespace tokens

No Comments

No Known Activations