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

1:0.06

2:0.09

3:0.06

4:0.11

5:0.08

6:0.08

7:0.09

8:0.08

9:0.06

10:0.07

11:0.07

Negative Logits

版

-1.62

BuyableInstoreAndOnline

-1.52

ModLoader

-1.48

 taxp

-1.43

 サーティワン

-1.38

HAHAHAHA

-1.35

fml

-1.32

 livest

-1.31

 LAST

-1.30

�

-1.30

POSITIVE LOGITS

ollah

1.42

itiveness

1.40

eer

1.38

iment

1.28

rous

1.28

ussion

1.26

 variation

1.26

imental

1.25

nosis

1.24

isation

1.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.