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

1:0.09

2:0.07

3:0.07

4:0.08

5:0.07

6:0.09

7:0.08

8:0.07

9:0.07

10:0.08

11:0.09

Negative Logits

 wise

-1.43

cens

-1.34

 measures

-1.33

 hind

-1.33

 prest

-1.31

-->

-1.28

 fact

-1.26

 traits

-1.25

 Aman

-1.25

 Conclusion

-1.24

POSITIVE LOGITS

BuyableInstoreAndOnline

2.09

MpServer

1.50

���

1.50

oké

1.50

ixel

1.46

FML

1.45

 Lauder

1.45

ixties

1.39

phabet

1.35

dinand

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.