INDEX

Explanations

attends to terms related to specific categories from various general tokens in the same or different contexts

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

0:0.40

1:0.17

2:0.13

3:0.06

4:0.05

5:0.03

6:0.05

7:0.07

Negative Logits

 oprot

-0.24

 Portail

-0.23

something

-0.23

}))

-0.23

Portail

-0.22

िखित

-0.22

lables

-0.21

 liev

-0.21

__':

-0.21

IZED

-0.20

POSITIVE LOGITS

bootstrapcdn

0.32

 فريبيس

0.31

MethodManager

0.26

useNewUrlParser

0.24

fetchone

0.24

السكان

0.24

enumii

0.24

ScopeManager

0.23

cshtml

0.22

ISupport

0.22

Activations Density 1.136%

attends to terms related to specific categories from various general tokens in the same or different contexts

No Comments

No Known Activations