INDEX

Explanations

references to religious texts, specifically 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

2:0.09

3:0.09

4:0.07

5:0.08

6:0.07

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

uterte

-3.13

arez

-2.82

ipal

-2.65

reenshot

-2.61

ovo

-2.61

ipl

-2.47

maximum

-2.46

htaking

-2.46

 Execution

-2.44

-2.42

POSITIVE LOGITS

 Frie

2.67

EH

2.52

 avail

2.49

NAD

2.48

 IEEE

2.43

 forthcoming

2.39

EE

2.39

Doctor

2.38

NI

2.37

Scotland

2.30

Activations Density 0.000%

references to religious texts, specifically the Quran

No Comments

No Known Activations