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

1:0.08

2:0.07

3:0.09

4:0.08

5:0.08

6:0.07

7:0.07

8:0.08

9:0.08

10:0.07

11:0.10

Negative Logits

eele

-2.63

$,

-2.53

 SPACE

-2.45

 Ferguson

-2.36

ciation

-2.34

DragonMagazine

-2.33

VG

-2.31

USD

-2.31

Reviewer

-2.28

ync

-2.26

POSITIVE LOGITS

pel

2.77

 laps

2.66

mares

2.52

 laun

2.48

afety

2.42

pell

2.38

�

2.31

 alarms

2.27

 Prot

2.22

 boil

2.21

Activations Density 0.000%

references to the Quran

No Comments

No Known Activations