INDEX

Explanations

instances of phrases related to expressing love and affection

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

0:0.04

1:0.02

2:0.19

3:0.02

4:0.31

5:0.06

6:0.02

7:0.02

8:0.05

9:0.15

10:0.04

11:0.02

Negative Logits

verage

-1.41

omet

-1.36

Wr

-1.34

��

-1.33

fif

-1.32

Dead

-1.30

INAL

-1.30

rea

-1.29

Form

-1.28

KK

-1.27

POSITIVE LOGITS

 injecting

1.41

 immersion

1.35

 clitor

1.34

 nurturing

1.30

 intimacy

1.30

 poetry

1.27

 solitude

1.26

 physic

1.25

 arts

1.23

 experimenting

1.23

Activations Density 0.009%

instances of phrases related to expressing love and affection

No Known Activations