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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.07

3:0.10

4:0.07

5:0.09

6:0.07

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 Loving

-1.34

 Guant

-1.33

 Fior

-1.30

 Bridges

-1.29

 Berks

-1.27

eering

-1.27

 Trayvon

-1.26

 Frie

-1.24

rieve

-1.24

 Lawyers

-1.23

POSITIVE LOGITS

ntax

1.39

ega

1.32

 brackets

1.30

 drawback

1.29

resy

1.28

canon

1.24

ministic

1.23

inite

1.22

 circumstance

1.22

 Deity

1.21

Activations Density 0.000%

No Known Activations

This feature has no known activations.