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

2:0.09

3:0.09

4:0.08

5:0.07

6:0.07

7:0.08

8:0.06

9:0.08

10:0.09

11:0.07

Negative Logits

›

-1.55

 Buster

-1.32

 wagon

-1.27

 possesses

-1.25

®,

-1.24

ngth

-1.24

 catcher

-1.23

Poké

-1.22

 transporter

-1.19

 brisk

-1.18

POSITIVE LOGITS

ertodd

1.42

Interstitial

1.42

GBT

1.38

 Tanz

1.37

 Shutterstock

1.36

\\\\\\\\

1.34

kinson

1.31

%"

1.29

terday

1.28

 Universities

1.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.