INDEX

Explanations

attends to token patterns related to data representation or programming constructs from subsequent tokens that specify their context or functionality

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

0:0.09

1:0.11

2:0.11

3:0.12

4:0.11

5:0.07

6:0.19

7:0.16

Negative Logits

StoryboardSegue

-0.45

GOTREF

-0.44

:])

-0.43

WriteBarrier

-0.42

AccessorTable

-0.42

 تضيفلها

-0.42

SharedCtor

-0.40

 ویکی‌پدیا

-0.40

 jScrollPane

-0.40

featureID

-0.38

POSITIVE LOGITS

ousal

0.25

‍

0.25

 Méndez

0.24

oar

0.23

жа

0.23

FARE

0.23

 beren

0.23

 epider

0.23

flä

0.23

󠁧

0.22

Activations Density 0.061%

attends to token patterns related to data representation or programming constructs from subsequent tokens that specify their context or functionality

No Comments

No Known Activations