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

1:0.08

2:0.08

3:0.09

4:0.07

5:0.08

6:0.07

7:0.08

8:0.07

9:0.08

10:0.09

11:0.08

Negative Logits

 paed

-1.40

cloth

-1.36

Christmas

-1.29

 Christmas

-1.29

 transf

-1.26

 Bapt

-1.25

wick

-1.25

ser

-1.22

maid

-1.20

Ped

-1.20

POSITIVE LOGITS

itiveness

1.65

 WATCHED

1.46

 sqor

1.45

ibliography

1.37

estones

1.36

ickr

1.35

awan

1.33

anwhile

1.30

 guiActive

1.28

phabet

1.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.