INDEX

Explanations

proper nouns and phrases related to personal stories and experiences, such as health struggles, music albums, societal issues, and legal battles

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

Head Attr Weights

0:0.06

1:0.02

2:0.15

3:0.20

4:0.07

5:0.10

6:0.04

7:0.02

8:0.10

9:0.09

10:0.07

11:0.03

Negative Logits

earances

-1.31

thood

-1.26

unia

-1.20

edIn

-1.20

agall

-1.19

oslav

-1.19

assies

-1.16

 elig

-1.15

ierrez

-1.14

�

-1.12

POSITIVE LOGITS

})

1.37

').

1.36

』

1.34

born

1.31

liest

1.27

 nucleus

1.25

ieth

1.24

]).

1.24

 outweigh

1.22

 ());

1.22

Activations Density 0.073%

proper nouns and phrases related to personal stories and experiences, such as health struggles, music albums, societal issues, and legal battles

No Known Activations