INDEX

Explanations

attends to negative symbols from tokens involving rotational transformations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.11

1:0.14

2:0.13

3:0.16

4:0.12

5:0.06

6:0.09

7:0.15

Negative Logits

&\

-0.20

lom

-0.19

пуль

-0.19

fir

-0.19

Pul

-0.19

피

-0.18

اج

-0.18

viv

-0.18

xfe

-0.18

Ephe

-0.18

POSITIVE LOGITS

 Jefus

0.44

 myſelf

0.44

 purpoſe

0.42

 Majefty

0.42

 Chriftian

0.41

 itſelf

0.40

 supérieurs

0.40

 Diſ

0.40

 Anſ

0.40

 Theſe

0.39

Activations Density 0.485%

attends to negative symbols from tokens involving rotational transformations

No Comments

No Known Activations