INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

0:0.07

1:0.08

2:0.08

3:0.08

4:0.10

5:0.07

6:0.09

7:0.07

8:0.07

9:0.07

10:0.09

11:0.07

Negative Logits

channelAvailability

-1.55

arians

-1.40

});

-1.40

assetsadobe

-1.39

 enshr

-1.35

ESA

-1.35

••

-1.30

 funding

-1.27

liners

-1.24

 Royale

-1.23

POSITIVE LOGITS

spir

1.67

Fuck

1.55

roma

1.48

urnal

1.41

circle

1.41

 funeral

1.38

 condol

1.36

animate

1.36

 Notting

1.35

utenberg

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.