INDEX

Explanations

terms associated with mandatory evacuation protocols

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.19

1:0.08

2:0.04

3:0.10

4:0.05

5:0.04

6:0.09

7:0.14

8:0.02

9:0.06

10:0.07

11:0.08

Negative Logits

dag

-2.80

angling

-2.67

 Parallel

-2.60

 infinity

-2.58

 Patent

-2.57

organic

-2.54

 assassin

-2.50

chery

-2.42

 symmetry

-2.38

 Phar

-2.37

POSITIVE LOGITS

 evac

5.91

 evacuation

5.29

 evacuated

4.79

 evacuate

4.46

 Edmonton

4.11

 relocation

3.63

Ev

3.52

 FEMA

3.51

 Calgary

3.44

 shelters

3.41

Activations Density 0.007%

terms associated with mandatory evacuation protocols

No Known Activations