INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-att/layer_0/width_16k/average_l0_61

Prompts (Dashboard)

16,384 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.05

2:0.00

3:0.03

4:0.07

5:0.15

6:0.07

7:0.09

8:0.01

9:0.04

10:0.03

11:0.01

12:0.26

13:0.01

14:0.01

15:0.05

Negative Logits

-0.94

the

-0.31

-0.25

-0.23

-0.21

১

-0.20

new

-0.19

-0.18

POSITIVE LOGITS

contentLoaded

0.72



0.69

ſicht

0.69

 Menſchen

0.69



0.68



0.68



0.68

 zwiſchen

0.68



0.68

<unused65>

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.