INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

1:0.07

2:0.08

3:0.09

4:0.08

5:0.09

6:0.08

7:0.09

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

 Registry

-2.58

 Atom

-2.54

uthor

-2.54

 ACTION

-2.46

 registrations

-2.42

 honor

-2.40

iership

-2.32

 Identity

-2.31

 registration

-2.28

️

-2.26

POSITIVE LOGITS

urb

2.89

 bikini

2.77

Pool

2.71

 hump

2.68

 Debor

2.65

rawdownloadcloneembedreportprint

2.54

natureconservancy

2.50

Nev

2.48

ˈ

2.46

anga

2.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.