INDEX

Explanations

references to locker rooms and related activities

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

0:0.10

1:0.05

2:0.03

3:0.04

4:0.07

5:0.02

6:0.14

7:0.26

8:0.02

9:0.04

10:0.06

11:0.11

Negative Logits

 Merchant

-2.29

 Sell

-2.20

 Notting

-2.18

stocks

-2.13

 miscar

-2.13

uild

-2.07

 Poll

-2.06

assies

-2.05

poll

-2.05

 Monk

-2.05

POSITIVE LOGITS

 locker

2.93

 restrooms

2.46

 coaches

2.42

 restroom

2.39

 fans

2.29

 pads

2.27

Coach

2.25

 coach

2.15

 athletic

2.13

 fandom

2.11

Activations Density 0.003%

references to locker rooms and related activities

No Known Activations