INDEX

Explanations

attends to numerical results or statistical terms from corresponding numerical references or identifiers

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

0:0.15

1:0.12

2:0.09

3:0.11

4:0.08

5:0.09

6:0.06

7:0.25

Negative Logits

 ddelweddau

-0.39

 Gwyn

-0.33

thâu

-0.32

はじめに

-0.32

 ويكيميديا

-0.31

ympto

-0.31

 esternos

-0.31

 Euphrates

-0.30

glEnd

-0.30

 Sputnik

-0.30

POSITIVE LOGITS

expandindo

0.28

Datuak

0.27

節

0.27

higan

0.27

 âgées

0.26

ETRY

0.26

SharedCtor

0.26

illet

0.26

 berk

0.25

dée

0.25

Activations Density 0.176%

attends to numerical results or statistical terms from corresponding numerical references or identifiers

No Comments

No Known Activations