INDEX

Explanations

attends from mathematical token patterns to their respective labeled categories

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

0:0.07

1:0.02

2:0.03

3:0.04

4:0.64

5:0.08

6:0.06

7:0.04

Negative Logits

↵

-0.33

 onOptions

-0.32

 communis

-0.32

-0.31

</em>

-0.30

zis

-0.30

POSITIVE LOGITS

tvguidetime

0.70

$.

0.63

IntoConstraints

0.63

0.62

脚注の使い方

0.58

 Paglinawan

0.56

RegressionTest

0.56

 autorytatywna

0.52

EndGlobalSection

0.52

^(@)

0.52

Activations Density 0.172%

attends from mathematical token patterns to their respective labeled categories

No Comments

No Known Activations