INDEX

Explanations

attends to statistical expressions or experimental results from tokens that denote statistical significance or comparative values

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

0:0.09

1:0.11

2:0.13

3:0.15

4:0.13

5:0.06

6:0.17

7:0.13

Negative Logits

 kasarigan

-0.34

AddTagHelper

-0.32

 ISNI

-0.31

 parseFrom

-0.29

GEBURTSDATUM

-0.28

 متعلقه

-0.28

SharedDtor

-0.27

Ӕ

-0.26

 архивлан

-0.25

MarshalTo

-0.25

POSITIVE LOGITS

 hàng

0.27

 remonte

0.26

 UIFont

0.26

IntoConstraints

0.25

emptyList

0.24

jahtera

0.24

harusnya

0.24

HomeAsUpEnabled

0.24

IMC

0.24

oodoo

0.24

Activations Density 0.000%

attends to statistical expressions or experimental results from tokens that denote statistical significance or comparative values

No Comments

No Known Activations