INDEX

Explanations

names of individuals named Michelle

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

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

0:0.13

1:0.03

2:0.21

3:0.08

4:0.11

5:0.06

6:0.03

7:0.02

8:0.03

9:0.16

10:0.06

11:0.02

Negative Logits

 largeDownload

-1.35

──

-1.29

 glim

-1.28

 Contents

-1.24

 abdom

-1.23

 subsistence

-1.20

 Flavoring

-1.20

 facult

-1.18

ModLoader

-1.16

ISION

-1.15

POSITIVE LOGITS

kh

1.52

ourn

1.46

raud

1.38

ohan

1.34

ohn

1.30

shaw

1.30

riot

1.27

wig

1.27

iso

1.26

itte

1.24

Activations Density 0.007%

names of individuals named Michelle

No Comments

No Known Activations