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

1:0.06

2:0.08

3:0.08

4:0.09

5:0.08

6:0.08

7:0.08

8:0.07

9:0.09

10:0.08

11:0.08

Negative Logits

merce

-1.44

 Oath

-1.40

LEASE

-1.37

 nonex

-1.32

 mainline

-1.29

 Twitch

-1.26

uyomi

-1.25

 Harmony

-1.24

quished

-1.22

 Reloaded

-1.17

POSITIVE LOGITS

lain

1.64

%]

1.56

Ut

1.50

Gou

1.40

Bat

1.39

mat

1.38

�

1.36

iem

1.33

National

1.32

 Fernandez

1.30

Activations Density 0.000%

No Known Activations

This feature has no known activations.