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

0:0.08

1:0.06

2:0.09

3:0.07

4:0.07

5:0.07

6:0.08

7:0.07

8:0.11

9:0.07

10:0.07

11:0.09

Negative Logits

Users

-1.46

sites

-1.39

}}}

-1.37

Normal

-1.36

normal

-1.33

DragonMagazine

-1.31

txt

-1.29

VAT

-1.29

objects

-1.28

 mRNA

-1.27

POSITIVE LOGITS

 Axel

1.61

 Pixie

1.43

erity

1.43

Gig

1.37

 Rhodes

1.30

 Methodist

1.30

rones

1.29

 Baal

1.28

 fundraiser

1.27

igi

1.26

Activations Density 0.000%

No Known Activations

This feature has no known activations.