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

0:0.08

1:0.07

2:0.09

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 Upper

-1.29

Amp

-1.28

Alpha

-1.28

覚醒

-1.27

FX

-1.24

 Agility

-1.23

dragon

-1.21

fol

-1.20

Pir

-1.17

Ops

-1.16

POSITIVE LOGITS

akeru

1.67

omsky

1.51

��

1.43

 Wilkinson

1.42

 lash

1.42

phasis

1.41

�

1.37

bish

1.35

━

1.29

 homosexuals

1.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.