INDEX

Explanations

attends to the token "id" from tokens marked with "id" that appear later in the sequences

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

0:0.06

1:0.14

2:0.06

3:0.04

4:0.13

5:0.43

6:0.04

7:0.06

Negative Logits

glo

-0.20

RenderAtEndOf

-0.20

<bos>

-0.20

ModelAdmin

-0.20

 sendiri

-0.19

 SUDOC

-0.19

 focus

-0.18

らう

-0.17

for

-0.16

blo

-0.16

POSITIVE LOGITS

 متعلقه

0.46

 resourceCulture

0.40

 MainAxisSize

0.36

setVerticalGroup

0.34

IntoConstraints

0.34

ChildIndex

0.34

ArgsConstructor

0.33

 consultato

0.33

 CommonModule

0.33

 وتسجيلات

0.32

Activations Density 0.035%

attends to the token "id" from tokens marked with "id" that appear later in the sequences

No Comments

No Known Activations