INDEX

Explanations

phrases and terms related to dates and scheduling

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.03

1:0.46

2:0.03

3:0.05

4:0.04

5:0.05

6:0.04

7:0.06

8:0.03

9:0.06

10:0.04

11:0.05

Negative Logits

覚醒

-2.96

tyr

-2.74

odi

-2.73

-2.54

 lapt

-2.50

usterity

-2.49

 TheNitromeFan

-2.49

oids

-2.44

uder

-2.38

Avg

-2.38

POSITIVE LOGITS

June

3.20

May

2.93

 June

2.89

May

2.83

ophers

2.82

may

2.76

 Might

2.71

 Likely

2.69

 Sixth

2.68

 doubtless

2.63

Activations Density 0.007%

phrases and terms related to dates and scheduling

No Known Activations