INDEX

Explanations

phrases indicating compliance or fitness for specific roles or activities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.00

2:0.07

3:0.04

4:0.07

5:0.02

6:0.41

7:0.12

8:0.03

9:0.03

10:0.08

11:0.06

Negative Logits

ベ

-1.36

 haunt

-1.29

 Ghosts

-1.23

 cryptocurrencies

-1.23

mable

-1.22

wolves

-1.21

iatrics

-1.21

 Dogs

-1.20

 eBook

-1.19

rences

-1.18

POSITIVE LOGITS

��

1.53

 Configuration

1.29

 artic

1.27

ypes

1.24

bodied

1.23

rouse

1.22

ovo

1.21

 Removal

1.18

enough

1.17

 arri

1.17

Activations Density 0.004%

phrases indicating compliance or fitness for specific roles or activities

No Comments

No Known Activations