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

0:0.09

1:0.07

2:0.08

3:0.08

4:0.09

5:0.09

6:0.07

7:0.07

8:0.09

9:0.07

10:0.07

11:0.08

Negative Logits

ngth

-2.73

 Creed

-2.58

 Shooter

-2.54

llah

-2.45

quickShipAvailable

-2.43

 disg

-2.29

rition

-2.29

quit

-2.27

 Ichigo

-2.21

Dir

-2.21

POSITIVE LOGITS

lez

2.78

 Wales

2.77

lington

2.67

RAF

2.65

IRO

2.63

YS

2.58

knit

2.54

 Mold

2.52

endor

2.52

 Zionism

2.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.