INDEX

Explanations

No Explanations Found

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.07

3:0.07

4:0.08

5:0.07

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.10

Negative Logits

emetery

-1.48

pty

-1.36

uca

-1.31

iola

-1.29

ools

-1.28

ridge

-1.27

ofer

-1.27

ILLE

-1.26

�

-1.25

�

-1.24

POSITIVE LOGITS

RTX

1.46

 Slug

1.27

 nutshell

1.24

 metabol

1.22

alys

1.20

 stunts

1.19

 intens

1.17

 trends

1.16

 outlook

1.15

 Duchess

1.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.