INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.07

1:0.07

2:0.09

3:0.07

4:0.08

5:0.09

6:0.07

7:0.07

8:0.09

9:0.09

10:0.07

11:0.07

Negative Logits

jew

-1.30

 Benghazi

-1.30

Fib

-1.26

 insanity

-1.26

 bullies

-1.26

Girls

-1.22

 circ

-1.20

 pupp

-1.18

 patri

-1.17

Pref

-1.17

POSITIVE LOGITS

 confir

1.43

ItemThumbnailImage

1.42

clair

1.41

 largeDownload

1.40

ˈ

1.39

href

1.28

 proble

1.28

oute

1.27

handle

1.26

版

1.26

Activations Density 0.000%

No Known Activations

This feature has no known activations.