INDEX

Explanations

phrases related to possession or ownership

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

Head Attr Weights

0:0.09

1:0.08

2:0.08

3:0.07

4:0.07

5:0.08

6:0.09

7:0.08

8:0.06

9:0.09

10:0.08

11:0.08

Negative Logits

cot

-2.62

›

-2.56

ricanes

-2.48

ennial

-2.43

�

-2.42

 stal

-2.39

fps

-2.38

ウス

-2.38

�

-2.37

century

-2.37

POSITIVE LOGITS

 Nissan

3.51

 Homeless

2.88

 Harlem

2.85

NYU

2.83

EA

2.81

 Audi

2.80

 Lear

2.78

 Frankie

2.70

 Bruno

2.69

 Teen

2.68

Activations Density 0.000%

phrases related to possession or ownership

No Known Activations