INDEX

Explanations

attends to repetition of certain terms or phrases from tokens that refer back to prior occurrences in the text

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

0:0.08

1:0.09

2:0.10

3:0.26

4:0.26

5:0.02

6:0.09

7:0.07

Negative Logits

hast

-0.23

dom

-0.22

Sidenav

-0.22

be

-0.22

har

-0.22

IM

-0.21

GeneratedMessage

-0.21

ges

-0.21

mp

-0.21

ass

-0.21

POSITIVE LOGITS

 kasarigan

0.39

 незавершена

0.38

AddTagHelper

0.38

 defaultstate

0.37

 jScrollPane

0.35

 privées

0.35

 للمعارف

0.35

InjectAttribute

0.33

WriteTagHelper

0.32

complexType

0.32

Activations Density 0.237%

attends to repetition of certain terms or phrases from tokens that refer back to prior occurrences in the text

No Comments

No Known Activations