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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.07

3:0.08

4:0.08

5:0.09

6:0.09

7:0.09

8:0.08

9:0.07

10:0.09

11:0.07

Negative Logits

Reviewer

-2.62

MpServer

-2.22

DragonMagazine

-2.08

aceous

-1.97

ombat

-1.94

rolet

-1.83

 autos

-1.78

 Flavoring

-1.77

achus

-1.77

 compan

-1.75

POSITIVE LOGITS

len

1.63

 breakout

1.62

 Pend

1.59

 Strat

1.57

digy

1.54

 Sting

1.53

bridge

1.53

 gloom

1.50

CVE

1.47

 Guantanamo

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.