INDEX

Explanations

No Explanations Found

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.09

3:0.08

4:0.07

5:0.08

6:0.08

7:0.07

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

Guard

-3.16

izoph

-2.82

KO

-2.71

 scrut

-2.69

zona

-2.56

 guardians

-2.54

Gun

-2.50

Benz

-2.48

 propos

-2.47

Lug

-2.44

POSITIVE LOGITS

terday

2.67

 裏�

2.48

nesota

2.46

 Rebel

2.42

netflix

2.37

atha

2.33

 multiplied

2.29

cycles

2.28

 Renaissance

2.26

NetMessage

2.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.