INDEX

Explanations

attends to tokens marked by "induced" from tokens relating to inflammation or activation

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

0:0.12

1:0.17

2:0.15

3:0.09

4:0.09

5:0.06

6:0.10

7:0.19

Negative Logits

↵

-0.24

General

-0.24

matchCondition

-0.23

urlopen

-0.22

<eos>

-0.22

kurat

-0.22

ithin

-0.21

form

-0.21

 General

-0.21

Flash

-0.21

POSITIVE LOGITS

 насељу

0.38

localctx

0.33

 يتيمه

0.32

 Italijanski

0.32

ruptedException

0.30

 CreateTagHelper

0.30

aringan

0.30

 onCancelled

0.29

بوابة

0.29

AccessorTable

0.29

Activations Density 1.225%

attends to tokens marked by "induced" from tokens relating to inflammation or activation

No Comments

No Known Activations