INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

0:0.10

1:0.07

2:0.07

3:0.06

4:0.09

5:0.07

6:0.09

7:0.08

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

jew

-1.61

emis

-1.48

lik

-1.47

luaj

-1.45

 disclaim

-1.39

atts

-1.35

fax

-1.33

toc

-1.33

cigarettes

-1.30

assed

-1.29

POSITIVE LOGITS

verning

1.62

enegger

1.56

�

1.47

�

1.45

ヴァ

1.44

ーテ

1.43

Enlarge

1.43

ォ

1.42

 Childhood

1.41

cation

1.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.