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

0:0.09

1:0.07

2:0.08

3:0.08

4:0.09

5:0.07

6:0.07

7:0.08

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

rius

-1.38

atin

-1.34

ainer

-1.32

ulf

-1.31

packing

-1.31

gro

-1.30

 reminded

-1.29

alle

-1.27

 Endurance

-1.27

idge

-1.26

POSITIVE LOGITS

 spheres

1.38

 sponsorship

1.38

 acceler

1.32

 Burst

1.32

 capac

1.30

ワ

1.28

CoC

1.26

 compe

1.25

ixel

1.25

 gimmick

1.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.