INDEX

Explanations

attends to the first token in the sequence from various coding-related 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.11

2:0.10

3:0.11

4:0.08

5:0.03

6:0.26

7:0.18

Negative Logits

GenerationType

-0.36

 initComponents

-0.36

HostException

-0.34

 createSprite

-0.32

ftagPool

-0.30

XtraEditors

-0.30

nastics

-0.28

 Autorisations

-0.28

ElementException

-0.28

böz

-0.27

POSITIVE LOGITS

 Roskov

0.32

 Opium

0.31

Autoritní

0.31

 AssemblyCulture

0.31

بوابة

0.31

textAppearance

0.31

 SEDS

0.30

Sinh

0.30

<bos>

0.30

 Gaby

0.29

Activations Density 0.107%

attends to the first token in the sequence from various coding-related tokens

No Comments

No Known Activations