INDEX

Explanations

attends to numerical tokens denoting counts or quantities from earlier tokens that also indicate similar counts or quantities

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

0:0.04

1:0.11

2:0.06

3:0.03

4:0.17

5:0.50

6:0.02

7:0.04

Negative Logits

 للمعارف

-0.29

 MOND

-0.27

таратура

-0.26

Personensuche

-0.26

Chham

-0.25

InputTagHelper

-0.25

 AssemblyTitle

-0.25

aarrggbb

-0.25

verwijspagina

-0.25

 وتسجيلات

-0.25

POSITIVE LOGITS

__":

0.24

DataMember

0.23

aufen

0.22

/*++

0.22

alloon

0.22

 پذ

0.21

 Salt

0.21

readystatechange

0.21

 electrónicos

0.21

lieder

0.20

Activations Density 0.260%

attends to numerical tokens denoting counts or quantities from earlier tokens that also indicate similar counts or quantities

No Comments

No Known Activations