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

0:0.07

1:0.09

2:0.09

3:0.07

4:0.07

5:0.07

6:0.08

7:0.09

8:0.08

9:0.07

10:0.07

11:0.09

Negative Logits

 Carbuncle

-1.54

lihood

-1.53

 inherit

-1.52

Geh

-1.45

ur

-1.42

etc

-1.42

 Kart

-1.35

 stroke

-1.35

Wiz

-1.34

Initialized

-1.34

POSITIVE LOGITS

backed

1.78

wen

1.73

 guiActiveUn

1.72

bard

1.70

heit

1.67

reb

1.66

sponsored

1.64

rowd

1.60

conservancy

1.56

roy

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.