INDEX

Explanations

attends to degree-related tokens from fields of study 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

0:0.10

1:0.15

2:0.12

3:0.05

4:0.07

5:0.03

6:0.12

7:0.32

Negative Logits

Autoritní

-0.43

 متعلقه

-0.38

 autorytatywna

-0.35

didSet

-0.35

PhysRevLett

-0.34

ViewImports

-0.33

IndentedString

-0.32

 EconPapers

-0.31

ReusableCell

-0.31

 مرئيه

-0.30

POSITIVE LOGITS

NameInMap

0.24

 Coates

0.22

!';

0.21

μένος

0.20

[++

0.20

 forstå

0.19

 Offisielt

0.19

 Site

0.19

reiter

0.19

 оби

0.19

Activations Density 0.065%

attends to degree-related tokens from fields of study tokens

No Comments

No Known Activations