INDEX

Explanations

No Explanations Found

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.08

3:0.08

4:0.08

5:0.08

6:0.06

7:0.08

8:0.08

9:0.08

10:0.07

11:0.09

Negative Logits

 unsub

-2.64

pmwiki

-2.62

nas

-2.56

azon

-2.51

nants

-2.48

 cass

-2.44

 reluct

-2.42

PST

-2.36

 clos

-2.28

zn

-2.26

POSITIVE LOGITS

2.36

 Nasa

2.35

 Roads

2.30

 […]

2.29

 mapping

2.24

Maps

2.23

Games

2.22

 Navigation

2.19

 Bearing

2.18

 Graphics

2.16

Activations Density 0.000%

No Known Activations

This feature has no known activations.