INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.05

2:0.09

3:0.09

4:0.08

5:0.08

6:0.07

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

ean

-1.46

¨

-1.44

bod

-1.43

 Christy

-1.39

abiding

-1.37

assian

-1.37

formation

-1.36

 meant

-1.31

ouse

-1.30

rose

-1.27

POSITIVE LOGITS

xit

1.70

 nanop

1.65

zik

1.55

 impe

1.50

 Mehran

1.44

Enlarge

1.41

adeon

1.41

omsky

1.40

 reapp

1.39

 Gates

1.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.