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

5:0.08

6:0.09

7:0.09

8:0.08

9:0.08

10:0.07

11:0.07

Negative Logits

 lett

-2.65

 actionGroup

-2.62

 Elliott

-2.47

�

-2.46

 whip

-2.42

 skilled

-2.38

 Bore

-2.35

 autom

-2.34

 hors

-2.32

Lod

-2.30

POSITIVE LOGITS

gaard

2.83

ALSE

2.62

odox

2.62

inventoryQuantity

2.60

Portland

2.58

iatus

2.48

wrong

2.47

wav

2.45

Sov

2.44

 Canaver

2.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.