INDEX

Explanations

attends to the token "m" from various coding-related tokens

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

0:0.57

1:0.10

2:0.06

3:0.04

4:0.04

5:0.05

6:0.04

7:0.07

Negative Logits

 opérés

-0.30

 loro

-0.29

roda

-0.28

 Persönlichkeit

-0.28

 manuales

-0.28

外部リンク

-0.27

hão

-0.27

íncia

-0.27

createStatement

-0.26

wys

-0.26

POSITIVE LOGITS

 تضيفلها

0.47

 autorytatywna

0.46

 AssemblyCulture

0.41

Демографія

0.40

nodoc

0.40

Spoljašnje

0.39

pulumi

0.39

errHandler

0.38

elemField

0.38

sidemargin

0.37

Activations Density 0.307%

attends to the token "m" from various coding-related tokens

No Comments

No Known Activations