INDEX

Explanations

attends to tokens that indicate names or titles from the surrounding context or description related to various subjects

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

1:0.11

2:0.07

3:0.06

4:0.07

5:0.02

6:0.25

7:0.28

Negative Logits

 esigen

-0.36

jetunion

-0.34

 cser

-0.31

 ferien

-0.31

jęt

-0.30

erequisites

-0.30

 Cymru

-0.29

>),

-0.28

Fon

-0.28

setIcon

-0.28

POSITIVE LOGITS

 AssemblyCulture

0.53

 referenties

0.50

الإنجليزية

0.48

Искәрмәләр

0.46

Abitanti

0.44

ReusableCell

0.43

MessageOf

0.42

migrationBuilder

0.39

vacy

0.39

]")]

0.39

Activations Density 0.218%

attends to tokens that indicate names or titles from the surrounding context or description related to various subjects

No Comments

No Known Activations