INDEX

Explanations

phrases indicating motion or dynamics in various contexts

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.02

1:0.02

2:0.09

3:0.11

4:0.02

5:0.04

6:0.03

7:0.08

8:0.09

9:0.30

10:0.07

11:0.08

Negative Logits

�

-1.55

五

-1.35

auga

-1.31

tains

-1.28

grave

-1.27

deal

-1.23

malink

-1.22

ulty

-1.22

 Seller

-1.19

�

-1.19

POSITIVE LOGITS

 roller

1.60

 concurrently

1.24

avascript

1.24

 hoops

1.23

 faithfully

1.21

Wad

1.20

 treadmill

1.19

 carts

1.16

 heels

1.15

 whirlwind

1.15

Activations Density 0.018%

phrases indicating motion or dynamics in various contexts

No Known Activations