INDEX

Explanations

attends to the last token of a specific category from various unrelated token references

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

0:0.07

1:0.09

2:0.08

3:0.11

4:0.15

5:0.06

6:0.27

7:0.13

Negative Logits

 ReactDOM

-0.39

djangoproject

-0.38

AntiForgeryToken

-0.37

PreferredItem

-0.36

migrationBuilder

-0.35

getDoctrine

-0.35

ThroughAttribute

-0.34

modelBuilder

-0.34

россий

-0.32

Facades

-0.32

POSITIVE LOGITS

 >=",

0.43

 EconPapers

0.41

 تضيفلها

0.35

 estekak

0.34

Földrajz

0.33

Tracce

0.32

dibujo

0.32

onUpdate

0.31

NUMX

0.31

 anuales

0.31

Activations Density 0.666%

attends to the last token of a specific category from various unrelated token references

No Comments

No Known Activations

attends to the last token of a specific category from various unrelated token references

No Comments

No Known Activations