INDEX

Explanations

No Explanations Found

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.08

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.07

9:0.07

10:0.07

11:0.07

Negative Logits

 captcha

-2.99

 Malays

-2.74

 nodd

-2.68

 tally

-2.64

apan

-2.53

 hump

-2.41

chuk

-2.39

 favourites

-2.38

tul

-2.37

 Tuls

-2.36

POSITIVE LOGITS

SPONSORED

2.96

 Decoder

2.95

2.87

 Consent

2.69

 Forge

2.69

 Legislation

2.65

 Technician

2.65

 Forensic

2.59

 Dealer

2.52

 Campus

2.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.