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

1:0.07

2:0.09

3:0.07

4:0.08

5:0.08

6:0.07

7:0.09

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

 Customs

-2.62

Cos

-2.53

Cov

-2.49

 extracts

-2.49

 intermedi

-2.49

 collaborator

-2.46

 customs

-2.41

 tuning

-2.39

 London

-2.38

 Transport

-2.37

POSITIVE LOGITS

retty

3.37

arnaev

3.28

xual

3.26

aiman

3.18

anka

3.17

zona

3.17

emate

3.16

cpu

2.99

ridor

2.97

aukee

2.92

Activations Density 0.000%

No Known Activations

This feature has no known activations.