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

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.09

10:0.08

11:0.08

Negative Logits

 Wisconsin

-3.15

Wes

-3.07

 Lindsey

-3.05

 Lindsay

-2.77

Wisconsin

-2.77

 Florida

-2.75

 Lansing

-2.72

 Nebraska

-2.71

 Illinois

-2.66

 Massachusetts

-2.66

POSITIVE LOGITS

 pigeon

3.46

ascript

2.99

rider

2.92

NetMessage

2.77

 Rabbit

2.76

ombat

2.75

 simultane

2.71

 circum

2.65

 proportional

2.65

 pony

2.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.