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

0:0.06

1:0.06

2:0.08

3:0.10

4:0.08

5:0.07

6:0.10

7:0.06

8:0.09

9:0.09

10:0.09

11:0.07

Negative Logits

DragonMagazine

-1.61

atform

-1.57

ortium

-1.52

iov

-1.45

ieri

-1.44

aird

-1.40

›

-1.40

vr

-1.37

NetMessage

-1.35

 warr

-1.30

POSITIVE LOGITS

 nonviolent

1.53

 biblical

1.39

laughs

1.32

 futile

1.29

 willful

1.28

 conservation

1.27

 poaching

1.27

 louder

1.26

)."

1.25

 generosity

1.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.