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

0:0.05

1:0.06

2:0.07

3:0.05

4:0.04

5:0.05

6:0.05

7:0.05

8:0.06

9:0.06

10:0.07

11:0.04

12:0.09

13:0.06

14:0.05

15:0.05

Negative Logits

-1.00

 Quad

-0.73

Fac

-0.73

Dex

-0.72

Tex

-0.72

 Dura

-0.71

Vac

-0.71

Lex

-0.71

Inf

-0.71

Rel

-0.71

POSITIVE LOGITS

 Wikiseite

0.55

 Menschheit

0.53

 Notwendigkeit

0.53

 Económica

0.51

 Verhältnisse

0.51

 setempat

0.50

 Absicht

0.50

 vuestros

0.49

 Gerechtigkeit

0.49

 Öffentlichkeit

0.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.