INDEX

Explanations

attends to tokens that are marked with asterisks, indicating a focus on certain highlighted variables or terms from surrounding tokens that are in brackets

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

0:0.03

1:0.06

2:0.04

3:0.03

4:0.22

5:0.52

6:0.03

7:0.03

Negative Logits

unesse

-0.23

 prés

-0.20

{{\

-0.20

EndTag

-0.20

mybatisplus

-0.20

diğini

-0.19

 BrowserRouter

-0.19

 Judge

-0.19

 disambiguazione

-0.19

POSITIVE LOGITS

Cyfeiriadau

0.43

\{\\

0.38

Билгалдахарш

0.37

 gyhoeddwyd

0.37

 насеље

0.36

XmlAccessType

0.36

Demografie

0.35

 kasarigan

0.33

 externi

0.33

🏾

0.33

Activations Density 1.234%

attends to tokens that are marked with asterisks, indicating a focus on certain highlighted variables or terms from surrounding tokens that are in brackets

No Comments

No Known Activations