INDEX

Explanations

attends to the subplot-related tokens from various initialization or configuration tokens in code contexts

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

0:0.12

1:0.17

2:0.13

3:0.08

4:0.09

5:0.07

6:0.09

7:0.20

Negative Logits

MigrationBuilder

-0.40

InjectAttribute

-0.39

ScopeManager

-0.37

 دیکھیے

-0.37

SourceChecksum

-0.35

Personendaten

-0.35

fjspx

-0.35

TestingModule

-0.34

GraphicsUnit

-0.34

parsedMessage

-0.33

POSITIVE LOGITS

存于互联网档案馆

0.24

macro

0.23

 mantenga

0.22

retz

0.22

gie

0.21

やってきた

0.21

 neutrality

0.21

 andra

0.20

 permita

0.20

 arada

0.20

Activations Density 0.019%

attends to the subplot-related tokens from various initialization or configuration tokens in code contexts

No Comments

No Known Activations