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

1:0.09

2:0.08

3:0.07

4:0.08

5:0.08

6:0.08

7:0.07

8:0.08

9:0.09

10:0.08

11:0.06

Negative Logits

 Sims

-2.77

�

-2.66

psc

-2.40

 Paige

-2.39

‎

-2.38

hess

-2.33

Parent

-2.31

 Abandon

-2.29

の�

-2.29

Season

-2.28

POSITIVE LOGITS

duino

3.26

asio

2.67

 caffe

2.61

 Dynamo

2.46

 nailed

2.45

 iPod

2.38

 wired

2.35

 Droid

2.27

 Azerb

2.25

USB

2.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.