INDEX

Explanations

attends to subsection tokens from preceding numeral or variable tokens in mathematical contexts

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

0:0.29

1:0.05

2:0.02

3:0.04

4:0.46

5:0.04

6:0.05

7:0.02

Negative Logits

 CURIAM

-0.53

 doInBackground

-0.50

 незавершена

-0.47

 }}"></

-0.47

SuppressMessage

-0.46

 HasFactory

-0.44

 onCreateView

-0.41

rawDesc

-0.41

tvguidetime

-0.41

Portale

-0.41

POSITIVE LOGITS

 side

0.37

 were

0.29

drucks

0.28

out

0.27

ebrow

0.27

not

0.27

 book

0.27

ὐ

0.26

he

0.26

 well

0.25

Activations Density 0.007%

attends to subsection tokens from preceding numeral or variable tokens in mathematical contexts

No Comments

No Known Activations