INDEX

Explanations

phrases related to notifications and alerts aimed at the reader

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

Head Attr Weights

0:0.02

1:0.02

2:0.12

3:0.14

4:0.08

5:0.02

6:0.07

7:0.26

8:0.02

9:0.04

10:0.12

11:0.04

Negative Logits

fman

-2.02

onds

-1.80

ingu

-1.78

oud

-1.74

 convinc

-1.72

alien

-1.69

olk

-1.69

omorphic

-1.68

edi

-1.68

ierrez

-1.67

POSITIVE LOGITS

 subscriptions

1.95

 subscription

1.94

 availability

1.70

 consultation

1.69

 Sched

1.66

 ordering

1.65

TBD

1.64

 rentals

1.63

Delivery

1.57

DragonMagazine

1.55

Activations Density 0.000%

phrases related to notifications and alerts aimed at the reader

No Known Activations