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

0:0.08

1:0.09

2:0.06

3:0.08

4:0.07

5:0.08

6:0.09

7:0.08

8:0.08

9:0.09

10:0.07

11:0.08

Negative Logits

atis

-1.48

htaking

-1.46

emic

-1.42

merce

-1.39

MSN

-1.34

icester

-1.32

 licences

-1.31

ittal

-1.30

fab

-1.30

bies

-1.29

POSITIVE LOGITS

aiman

1.37

ibble

1.33

olt

1.29

神

1.27

asha

1.26

 Loren

1.25

agonist

1.25

canon

1.23

oute

1.20

 Coil

1.19

Activations Density 0.000%

No Known Activations

This feature has no known activations.