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

2:0.08

3:0.07

4:0.08

5:0.09

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

idable

-1.46

riad

-1.42

SPONSORED

-1.33

orses

-1.32

 mutants

-1.27

MAG

-1.25

omination

-1.24

aires

-1.23

MAG

-1.22

iola

-1.22

POSITIVE LOGITS

 nutshell

1.45

 Payments

1.35

~~~~

1.33

ggle

1.29

 proble

1.29

kinson

1.26

enture

1.21

cision

1.20

 Writ

1.19

thodox

1.17

Activations Density 0.000%

No Known Activations

This feature has no known activations.