INDEX

Explanations

specific phrases related to laws, regulations, and official documents

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

0:0.04

1:0.03

2:0.22

3:0.04

4:0.33

5:0.04

6:0.03

7:0.02

8:0.06

9:0.07

10:0.04

11:0.02

Negative Logits

wings

-1.52

retty

-1.48

eff

-1.36

yang

-1.35

igans

-1.33

wig

-1.30

LET

-1.29

ufact

-1.25

 ABOUT

-1.25

hillary

-1.24

POSITIVE LOGITS

Repeat

1.51

Repe

1.43

ctory

1.34

Strike

1.32

]}

1.30

シャ

1.28

ction

1.26

 depreciation

1.25

RT

1.24

 Prohibition

1.23

Activations Density 0.005%

specific phrases related to laws, regulations, and official documents

No Known Activations