INDEX

Explanations

keywords related to theology and reflections on God's nature and actions

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

mentions of God and divine attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.25

1:0.03

2:0.06

3:0.03

4:0.08

5:0.07

6:0.14

7:0.04

8:0.04

9:0.04

10:0.11

11:0.04

Negative Logits

ten

-1.53

neau

-1.50

oute

-1.43

ockey

-1.39

actionDate

-1.38

ritz

-1.37

incial

-1.37

rete

-1.36

gomery

-1.35

lege

-1.35

POSITIVE LOGITS

 Himself

1.57

 beings

1.49

 embodied

1.48

 incarn

1.41

 commanded

1.39

 disemb

1.36

 nomine

1.35

 answers

1.34

 Almighty

1.33

 immortal

1.33

Activations Density 0.023%

keywords related to theology and reflections on God's nature and actions

mentions of God and divine attributes

No Comments

No Known Activations