INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

1:0.09

2:0.08

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.09

11:0.07

Negative Logits

►

-2.78

 silenced

-2.45

enthal

-2.42

TOR

-2.37

 accur

-2.35

 wisely

-2.33

 turrets

-2.28

EY

-2.27

 psychiat

-2.23

*/

-2.22

POSITIVE LOGITS

regate

3.02

asc

2.81

iso

2.70

legate

2.65

 cabal

2.52

org

2.52

 Commun

2.52

 Panc

2.50

arc

2.45

Registered

2.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.