INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.11

2:0.09

3:0.09

4:0.07

5:0.07

6:0.07

7:0.07

8:0.07

9:0.07

10:0.08

11:0.07

Negative Logits

 Herz

-1.65

sic

-1.65

 Topic

-1.63

 newsletters

-1.62

 Schwarz

-1.60

 guiName

-1.58

 Scrib

-1.55

 Switzerland

-1.54

 Warner

-1.54

 Hobby

-1.52

POSITIVE LOGITS

gdala

2.30

kas

2.04

WithNo

2.02

chal

1.96

lopp

1.96

*/(

1.87

xtap

1.83

 therap

1.80

Shot

1.78

BIP

1.78

Activations Density 0.000%

No Known Activations

This feature has no known activations.