INDEX

Explanations

concepts related to complexity

New Auto-Interp

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

Head Attr Weights

0:0.07

1:0.08

2:0.09

3:0.08

4:0.07

5:0.07

6:0.09

7:0.09

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

phabet

-1.73

ventures

-1.72

 looph

-1.56

 Karn

-1.51

 solicitation

-1.49

ensing

-1.49

 recruitment

-1.48

 pitches

-1.46

 chall

-1.46

LAT

-1.44

POSITIVE LOGITS

isSpecialOrderable

2.18

rafted

1.90

ecause

1.78

initely

1.74

\.

1.72

 blush

1.65

acea

1.64

endif

1.64

ea

1.64

aunt

1.63

Activations Density 0.000%

concepts related to complexity

No Known Activations