INDEX

Explanations

phrases related to the concept of value or worth

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

Head Attr Weights

0:0.07

1:0.03

2:0.13

3:0.09

4:0.14

5:0.05

6:0.02

7:0.02

8:0.12

9:0.20

10:0.05

11:0.02

Negative Logits

usra

-1.47

razil

-1.25

azed

-1.20

idem

-1.19

xual

-1.19

ophobic

-1.16

 vomiting

-1.15

jit

-1.12

Nusra

-1.12

 Canaver

-1.11

POSITIVE LOGITS

 investments

1.44

smanship

1.37

 treasures

1.33

 Unlock

1.32

 possessions

1.28

 precious

1.28

 talents

1.27

 Gems

1.25

 priceless

1.23

 investment

1.23

Activations Density 0.014%

phrases related to the concept of value or worth

No Known Activations