INDEX

Explanations

attends to the numeric indicators following the token "s" from adjacent tokens

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

0:0.16

1:0.17

2:0.17

3:0.05

4:0.06

5:0.03

6:0.09

7:0.22

Negative Logits

FFIX

-0.32

providedIn

-0.30

hasMoreElements

-0.29

 trás

-0.29

resizingMask

-0.28

borderSide

-0.28

awaiter

-0.27

눠

-0.27

Примітки

-0.26

nonatomic

-0.26

POSITIVE LOGITS

Efq

0.39

 Majefty

0.38

__":

0.36

__":

0.34

."],

0.34

 HasFactory

0.33

 Monfieur

0.33

$")

0.33

ſelves

0.33

 houſe

0.33

Activations Density 0.041%

attends to the numeric indicators following the token "s" from adjacent tokens

No Comments

No Known Activations