INDEX

Explanations

No Explanations Found

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.07

3:0.08

4:0.06

5:0.07

6:0.10

7:0.09

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

tails

-1.31

 depends

-1.26

nels

-1.21

frames

-1.21

 isol

-1.18

classes

-1.18

 doors

-1.17

 confines

-1.15

 attachments

-1.14

bos

-1.14

POSITIVE LOGITS

azeera

1.41

 Gamble

1.33

maxwell

1.30

 Nept

1.30

fol

1.28

 Gins

1.23

Kev

1.22

 Polic

1.20

Aad

1.20

senal

1.20

Activations Density 0.000%

No Known Activations

This feature has no known activations.