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

1:0.08

2:0.08

3:0.06

4:0.08

5:0.07

6:0.07

7:0.09

8:0.07

9:0.08

10:0.08

11:0.09

Negative Logits

nep

-2.71

 describ

-2.56

sim

-2.51

aiman

-2.42

aban

-2.41

inav

-2.38

 rept

-2.38

 pitted

-2.37

 Siber

-2.37

-2.36

POSITIVE LOGITS

Leaks

2.80

 Letter

2.65

 Compliance

2.54

 Hilbert

2.51

 Fell

2.49

 Grounds

2.43

 Patent

2.39

————

2.36

 briefs

2.30

ß

2.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.