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

3:0.09

4:0.08

5:0.07

6:0.08

7:0.08

8:0.07

9:0.09

10:0.07

11:0.09

Negative Logits

 Metropolitan

-2.84

 Guardian

-2.43

 Veil

-2.38

-2.32

 enduring

-2.29

 Dele

-2.27

 Allen

-2.26

�

-2.26

 Pole

-2.17

 passer

-2.12

POSITIVE LOGITS

terness

3.30

utonium

2.86

��

2.76

izu

2.67

maxwell

2.65

ciation

2.61

interstitial

2.58

arma

2.56

reed

2.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.