INDEX

Explanations

phrases related to negative experiences or criticism

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.05

1:0.04

2:0.07

3:0.03

4:0.05

5:0.03

6:0.21

7:0.04

8:0.05

9:0.29

10:0.02

11:0.05

Negative Logits

 Conver

-3.74

 Cthulhu

-3.58

ulhu

-3.52

��

-3.48

 caffeine

-3.36

usalem

-3.32

ECO

-3.27

 Cable

-3.26

-3.24

�

-3.24

POSITIVE LOGITS

 Miss

9.88

Miss

9.73

 MISS

8.26

miss

8.14

 miss

6.30

 Mississ

5.92

 Mississippi

5.22

 misses

4.81

MIA

4.47

MS

4.33

Activations Density 0.011%

phrases related to negative experiences or criticism

No Known Activations