INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.08

3:0.08

4:0.09

5:0.07

6:0.07

7:0.09

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

idious

-1.58

itsch

-1.56

orno

-1.56

incerity

-1.38

 lipstick

-1.38

 perfume

-1.33

ensual

-1.33

 Fourth

-1.30

Crime

-1.29

inus

-1.28

POSITIVE LOGITS

SourceFile

1.55

Pwr

1.40

裏

1.38

 employ

1.33

},"

1.32

 Enix

1.29

 offshore

1.23

 Antar

1.22

_(

1.21

 Technologies

1.20

Activations Density 0.000%

No Known Activations

This feature has no known activations.