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

0:0.07

1:0.07

2:0.09

3:0.08

4:0.09

5:0.07

6:0.07

7:0.09

8:0.06

9:0.08

10:0.09

11:0.08

Negative Logits

utters

-1.37

 Spokane

-1.35

uckland

-1.32

orrow

-1.32

tesque

-1.31

ongyang

-1.29

uton

-1.26

lear

-1.26

ipeg

-1.25

itic

-1.24

POSITIVE LOGITS

 VIDEOS

1.43

VERTISEMENT

1.42

 Bounty

1.23

DragonMagazine

1.18

ゴン

1.17

 Kardash

1.17

soDeliveryDate

1.16

xual

1.15

 Rath

1.15

 actionGroup

1.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.