INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

0:0.09

1:0.08

2:0.08

3:0.08

4:0.09

5:0.08

6:0.08

7:0.07

8:0.09

9:0.08

10:0.07

11:0.07

Negative Logits

 packaged

-1.47

 labeled

-1.38

rily

-1.37

 editions

-1.37

Catalog

-1.36

 advertisers

-1.36

 fractions

-1.35

boards

-1.33

 iterations

-1.29

 sequences

-1.28

POSITIVE LOGITS

ミ

1.59

 murd

1.50

 seiz

1.39

 裏�

1.38

 Mata

1.36

 Leilan

1.36

 confir

1.34

 corrid

1.32

alam

1.29

�

1.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.