INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.07

1:0.08

2:0.08

3:0.07

4:0.07

5:0.08

6:0.08

7:0.09

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

abeth

-1.49

 unto

-1.43

abet

-1.34

 forgiven

-1.32

Compan

-1.30

Eld

-1.28

 inval

-1.27

 dies

-1.23

 desc

-1.22

 farewell

-1.21

POSITIVE LOGITS

ijing

1.66

iasco

1.58

livious

1.54

zhou

1.53

 Shutterstock

1.38

social

1.35

mercial

1.32

 PowerPoint

1.32

peak

1.29

 Spotify

1.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.