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

1:0.08

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.10

8:0.07

9:0.07

10:0.07

11:0.07

Negative Logits

shapeshifter

-2.81

 guiName

-2.80

rick

-2.70

Alex

-2.58

 sonic

-2.55

church

-2.48

acus

-2.46

 reneg

-2.46

bryce

-2.45

asc

-2.39

POSITIVE LOGITS

 Nets

2.59

 Serie

2.54

 Topics

2.48

anguage

2.46

stract

2.42

 Patent

2.42

},{"

2.37

ongevity

2.35

iewicz

2.28

grain

2.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.