INDEX

Explanations

attends to negation or inquiry-related tokens from the following tokens making statements or requesting information

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

0:0.10

1:0.12

2:0.08

3:0.10

4:0.10

5:0.05

6:0.24

7:0.17

Negative Logits

Autoritní

-0.54

 Meksiku

-0.49

UserScript

-0.48

 gynhyrchwyd

-0.45

oa̍t

-0.44

 المعيارى

-0.41

Obrázky

-0.40

 PeEnEo

-0.40

 ویکی‌پدی

-0.40

 يتيمه

-0.39

POSITIVE LOGITS

તિ

0.29

 ***!

0.26

 Range

0.26

ات

0.25

Range

0.25

ず

0.25

depend

0.24

μιουργ

0.24

zeß

0.24

qai

0.23

Activations Density 0.032%

attends to negation or inquiry-related tokens from the following tokens making statements or requesting information

No Comments

No Known Activations