INDEX

Explanations

references to personal experiences and emotional reactions

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.18

1:0.10

2:0.08

3:0.05

4:0.04

5:0.03

6:0.07

7:0.10

8:0.03

9:0.06

10:0.16

11:0.06

Negative Logits

Luc

-3.44

Luc

-3.25

IU

-3.21

у

-3.20

IU

-3.18

 Lumia

-3.16

Sv

-3.15

 ObamaCare

-3.08

 menstrual

-2.98

 Constantin

-2.91

POSITIVE LOGITS

 Bark

7.63

 Barker

7.53

 bark

5.35

 Barkley

4.83

ark

3.74

 barking

3.73

 Bane

3.69

Bak

3.52

Bridge

3.45

 goblin

3.41

Activations Density 0.001%

references to personal experiences and emotional reactions

No Known Activations