INDEX

Explanations

affirmations or confirmations about situations or decisions

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

Head Attr Weights

0:0.06

1:0.09

2:0.04

3:0.04

4:0.02

5:0.16

6:0.03

7:0.01

8:0.25

9:0.09

10:0.08

11:0.08

Negative Logits

achus

-2.05

FTWARE

-1.56

ternity

-1.53

ebus

-1.46

adier

-1.46

untled

-1.44

onica

-1.40

uliffe

-1.40

anmar

-1.39

assis

-1.37

POSITIVE LOGITS

 smell

1.39

 homophobic

1.38

 odor

1.26

..."

1.24

 antiquity

1.21

 homophobia

1.21

 latex

1.19

 Icar

1.18

Iz

1.18

 smells

1.17

Activations Density 0.205%

affirmations or confirmations about situations or decisions

No Known Activations