INDEX

Explanations

phrases that indicate giving or receiving permission

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.03

1:0.04

2:0.07

3:0.06

4:0.02

5:0.05

6:0.06

7:0.06

8:0.08

9:0.30

10:0.08

11:0.11

Negative Logits

nces

-1.42

 revolving

-1.29

 difficulty

-1.26

paralle

-1.26

borough

-1.20

tip

-1.19

itiveness

-1.16

ths

-1.15

attribute

-1.15

 inherent

-1.15

POSITIVE LOGITS

 airspace

1.46

uberty

1.41

Continue

1.30

PDATE

1.27

 Quit

1.27

 negotiate

1.25

 landfall

1.25

 hostilities

1.23

activate

1.21

write

1.19

Activations Density 0.007%

phrases that indicate giving or receiving permission

No Known Activations