INDEX

Explanations

attends to instances of the term "course" from related "of" tokens

oai_attention-head · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k

Configuration

google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

0:0.77

1:0.01

2:0.01

3:0.02

4:0.12

5:0.01

6:0.01

7:0.02

Negative Logits

 then

-0.39

of

-0.33

as

-0.29

Зноскі

-0.29

it

-0.29

 that

-0.27

not

-0.27

❦

-0.26

at

-0.26

Bakgrunnsstoff

-0.26

POSITIVE LOGITS

 surla

0.53

 disambiguazione

0.52

 kaarangay

0.51

 AssemblyProduct

0.50

"]);

0.49

AddTagHelper

0.49

yntaxException

0.49

ftagPool

0.48

 '');

0.47

verwijspagina

0.45

Activations Density 0.018%

attends to instances of the term "course" from related "of" tokens

No Comments

No Known Activations