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

0:0.08

1:0.09

2:0.08

3:0.07

4:0.08

5:0.09

6:0.08

7:0.09

8:0.07

9:0.08

10:0.08

11:0.07

Negative Logits

 warr

-2.94

 pall

-2.55

 pneum

-2.53

 phys

-2.46

 grunt

-2.37

 ship

-2.36

 Porsche

-2.36

BO

-2.33

 thermal

-2.33

FD

-2.31

POSITIVE LOGITS

aiman

3.60

oppers

2.97

 Crimes

2.95

®,

2.62

arag

2.60

ayers

2.59

 Cases

2.58

athi

2.58

2.56

crim

2.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.