INDEX

Explanations

References to the Quran

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

0:0.08

1:0.09

2:0.08

3:0.08

4:0.08

5:0.07

6:0.07

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 crore

-2.44

arth

-2.39

RSS

-2.38

 devs

-2.37

 festivals

-2.36

 advertisements

-2.31

Weather

-2.31

 Harbour

-2.28

IRC

-2.27

Chinese

-2.27

POSITIVE LOGITS

osexual

2.76

ione

2.66

vantage

2.53

vill

2.40

 Prosper

2.39

 sket

2.38

efer

2.37

olate

2.33

iece

2.33

ivan

2.32

Activations Density 0.000%

References to the Quran

No Comments

No Known Activations