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

0:0.07

1:0.07

2:0.09

3:0.07

4:0.07

5:0.08

6:0.09

7:0.08

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

adelphia

-2.77

 gren

-2.74

 destro

-2.60

 felon

-2.50

rimp

-2.46

 greed

-2.43

 scorp

-2.39

usterity

-2.39

uncle

-2.37

 blade

-2.30

POSITIVE LOGITS

 Communities

2.85

Cy

2.84

Ev

2.75

 Cong

2.74

Mit

2.71

 Diet

2.63

 Ples

2.57

Met

2.57

 Latvia

2.56

 Athe

2.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.