INDEX

Explanations

phrases related to significant or impactful actions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.02

1:0.01

2:0.17

3:0.10

4:0.05

5:0.03

6:0.18

7:0.02

8:0.16

9:0.07

10:0.07

11:0.07

Negative Logits

jee

-1.71

 Dane

-1.34

lly

-1.34

[|

-1.33

 clust

-1.31

 evenly

-1.29

 differently

-1.26

Klu

-1.25

bably

-1.22

xon

-1.19

POSITIVE LOGITS

afort

1.46

DragonMagazine

1.41

 FIGHT

1.26

 INFORMATION

1.26

 Detected

1.25

 Submission

1.23

archives

1.20

 Enemies

1.18

INFO

1.17

 Emin

1.17

Activations Density 0.005%

phrases related to significant or impactful actions

No Comments

No Known Activations