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

1:0.07

2:0.08

3:0.07

4:0.08

5:0.08

6:0.07

7:0.09

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

 Alexa

-3.27

 McGregor

-3.15

 Frankie

-3.03

 Coco

-3.01

 Tune

-2.91

FF

-2.79

 Wellington

-2.79

Lee

-2.71

 MacDonald

-2.71

FX

-2.67

POSITIVE LOGITS

ulsion

3.05

Wisconsin

2.93

ior

2.90

Michigan

2.86

�

2.84

Iraq

2.78

Iowa

2.77

iffs

2.69

usky

2.68

hap

2.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.