INDEX

Explanations

attends to token patterns related to "Acu" from "Acuité" tokens

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

0:0.06

1:0.01

2:0.03

3:0.01

4:0.65

5:0.16

6:0.01

7:0.03

Negative Logits

ثيق

-0.51

intios

-0.45

:]:

-0.41

 مشارکت‌کنندگان

-0.41

лактика

-0.40

closedir

-0.39

cknowledge

-0.39

🏾

-0.39

nemia

-0.38

Gij

-0.38

POSITIVE LOGITS

DockStyle

0.40

mybatisplus

0.34

MigrationBuilder

0.33

↵

0.32

abestanden

0.29

 internetowa

0.28

xtype

0.27

Rhestr

0.27

withIdentifier

0.26

Activations Density 3.129%

attends to token patterns related to "Acu" from "Acuité" tokens

No Comments

No Known Activations