INDEX

Explanations

attends to specific names or entities marked by both double asterisks and double square brackets, indicating a focus on significant individuals or topics

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

0:0.05

1:0.14

2:0.04

3:0.03

4:0.10

5:0.52

6:0.03

7:0.04

Negative Logits

 navideños

-0.35

ülerin

-0.33

ByteBuf

-0.32

IBOutlet

-0.30

ordnet

-0.29

гата

-0.27

 penas

-0.27

owohl

-0.27

তথ্যসূত্র

-0.26

Slayer

-0.26

POSITIVE LOGITS

dehyde

0.38

Hozzáférés

0.36

 становника

0.35

 Վերցված

0.35

addPreferredGap

0.35

IANGLES

0.35

 Heber

0.34

unately

0.32

もの

0.31

loroethene

0.31

Activations Density 0.081%

attends to specific names or entities marked by both double asterisks and double square brackets, indicating a focus on significant individuals or topics

No Comments

No Known Activations