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

0:0.06

1:0.04

2:0.07

3:0.06

4:0.11

5:0.04

6:0.05

7:0.05

8:0.05

9:0.06

10:0.05

11:0.05

12:0.06

13:0.07

14:0.06

15:0.04

Negative Logits

 ſte

-0.52

 corne

-0.48

 ſind

-0.46

 cerv

-0.44

 fubject

-0.43

 carri

-0.43

 itſelf

-0.42

 Mono

-0.42

 terr

-0.42

 unſ

-0.41

POSITIVE LOGITS

 niebla

0.61

 desmotivaciones

0.61

 asamblea

0.60

 disfraces

0.59

 venganza

0.59

 infancia

0.59

 antemano

0.58

 transparencia

0.58

 prefeitura

0.58

 esclavos

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.