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

0:0.06

1:0.07

2:0.09

3:0.08

4:0.08

5:0.07

6:0.09

7:0.10

8:0.07

9:0.06

10:0.09

11:0.08

Negative Logits

nt

-1.50

hod

-1.41

*:

-1.35

tion

-1.35

learn

-1.34

intel

-1.29

Invalid

-1.28

 respons

-1.27

:=

-1.23

uther

-1.22

POSITIVE LOGITS

enegger

1.56

erey

1.54

Tsu

1.34

 Ambro

1.34

士

1.32

mares

1.30

 Reilly

1.27

 Vaugh

1.26

 Canaver

1.23

vre

1.21

Activations Density 0.000%

No Known Activations

This feature has no known activations.