INDEX

Explanations

attends to function-related tokens from related preparer tokens

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

0:0.08

1:0.07

2:0.08

3:0.05

4:0.07

5:0.03

6:0.12

7:0.46

Negative Logits

Lähteet

-0.22

fitrión

-0.20

ografija

-0.20

,”

-0.20

 חיצוניים

-0.19

página

-0.19

 withRouter

-0.19

 pureza

-0.18

 Edelman

-0.18

InstrumentedTest

-0.18

POSITIVE LOGITS

WEBPACK

0.33

requireNonNull

0.28

RTLD

0.28

Doi

0.28

AddTagHelper

0.28

脚注の使い方

0.27

 digress

0.27

 IBOutlet

0.27

็จ

0.26

setVerticalGroup

0.26

Activations Density 0.797%

attends to function-related tokens from related preparer tokens

No Comments

No Known Activations