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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.07

2:0.08

3:0.09

4:0.08

5:0.07

6:0.07

7:0.07

8:0.09

9:0.07

10:0.09

11:0.06

Negative Logits

DAQ

-1.51

apters

-1.43

undown

-1.43

Tw

-1.40

Motor

-1.40

 wavelength

-1.36

Join

-1.36

Series

-1.35

Scale

-1.34

romeda

-1.33

POSITIVE LOGITS

 Bahamas

1.39

enance

1.32

 foreigner

1.31

 mouths

1.28

ophobia

1.27

 excuses

1.26

 ditch

1.24

 honestly

1.24

 deserve

1.23

 guilt

1.21

Activations Density 0.000%

No Known Activations

This feature has no known activations.