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

2:0.07

3:0.07

4:0.07

5:0.08

6:0.09

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

 Tayyip

-2.64

knife

-2.62

 Isis

-2.59

Nic

-2.57

Marie

-2.56

Nik

-2.53

ı

-2.47

 Erdogan

-2.46

 EDIT

-2.42

 Anat

-2.38

POSITIVE LOGITS

 waits

2.51

 Greenwich

2.41

)</

2.37

 conventions

2.35

 convention

2.33

 conservation

2.33

 safeguard

2.30

 safegu

2.29

 wards

2.27

 ordinances

2.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.