INDEX

Explanations

attends to the token "for" from related tokens that follow

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

0:0.08

1:0.10

2:0.07

3:0.11

4:0.09

5:0.07

6:0.30

7:0.13

Negative Logits

WithIOException

-0.38

/.../

-0.28

enské

-0.26

 tartalomajánló

-0.26

long

-0.25

 Millennium

-0.25

Long

-0.24

 long

-0.24

 recognising

-0.23

 queries

-0.23

POSITIVE LOGITS

ymce

0.45

 Chwiliwch

0.42

ViewFeatures

0.42

RectangleBorder

0.41

riwal

0.40

VersionUID

0.40

MemoryWarning

0.40

tvguidetime

0.39

beitet

0.39

Пото

0.39

Activations Density 0.001%

attends to the token "for" from related tokens that follow

No Comments

No Known Activations