INDEX

Explanations

attends to protective tokens from their corresponding vulnerable 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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.03

2:0.05

3:0.04

4:0.51

5:0.11

6:0.03

7:0.12

Negative Logits

NameInMap

-0.54

Personendaten

-0.48

 initComponents

-0.39

 OFDb

-0.37

IndentedString

-0.36

 sanno

-0.34

 Walkover

-0.34

 المعيارى

-0.34

 Administrativna

-0.31

 fides

-0.31

POSITIVE LOGITS

endphp

0.53

/*

0.43

antaranya

0.41

》.

0.40

?>

0.40

 toJson

0.40

SupportActionBar

0.40

 protections

0.39

assertRaises

0.38

defineProperty

0.38

Activations Density 0.081%

attends to protective tokens from their corresponding vulnerable tokens

No Comments

No Known Activations