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

0:0.08

1:0.08

2:0.10

3:0.08

4:0.09

5:0.08

6:0.08

7:0.07

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

isy

-1.52

akia

-1.51

rule

-1.50

ombat

-1.48

 subst

-1.46

rue

-1.46

interpret

-1.41

ines

-1.39

ativity

-1.38

dict

-1.37

POSITIVE LOGITS

BuyableInstoreAndOnline

1.91

 Carib

1.71

ModLoader

1.53

 Agric

1.52

 Jenn

1.50

Tuc

1.47

 Surviv

1.44

okemon

1.44

 millenn

1.43

 Philippines

1.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.