INDEX

Explanations

No Explanations Found

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

3:0.08

4:0.07

5:0.09

6:0.08

7:0.09

8:0.07

9:0.08

10:0.09

11:0.08

Negative Logits

 ObamaCare

-3.33

 Nevada

-3.09

ACA

-2.89

NYC

-2.76

 Obamacare

-2.73

 Packers

-2.71

 Medicare

-2.68

 Congressional

-2.67

 Cohn

-2.63

 Veterans

-2.57

POSITIVE LOGITS

Rust

3.29

 strut

2.85

grain

2.78

 Tiff

2.72

Arch

2.62

hedon

2.56

 flush

2.54

flush

2.54

jac

2.50

Bus

2.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.