INDEX

Explanations

references to ordinal numbers and their significance in various contexts

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.01

1:0.01

2:0.17

3:0.05

4:0.09

5:0.03

6:0.03

7:0.22

8:0.03

9:0.03

10:0.08

11:0.18

Negative Logits

wives

-1.52

 Cabin

-1.41

Town

-1.41

 Mermaid

-1.38

hered

-1.38

umbered

-1.37

stories

-1.36

 Soup

-1.35

idays

-1.34

united

-1.31

POSITIVE LOGITS

 curs

1.47

 classmate

1.39

 probe

1.28

 cush

1.27

haus

1.26

etts

1.26

 drill

1.24

hower

1.24

 pane

1.23

 utter

1.20

Activations Density 0.003%

references to ordinal numbers and their significance in various contexts

No Known Activations