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

1:0.07

2:0.08

3:0.07

4:0.08

5:0.08

6:0.08

7:0.10

8:0.07

9:0.07

10:0.08

11:0.07

Negative Logits

 anyways

-3.06

 anyway

-2.85

 Monica

-2.45

 Michele

-2.45

 nonetheless

-2.33

 Bosnia

-2.29

 curing

-2.27

 Manny

-2.27

bed

-2.24

 thereafter

-2.23

POSITIVE LOGITS

天

2.90

 Formation

2.83

 裏�

2.70

 Volunteer

2.61

 Orange

2.58

 Dominion

2.56

 Witness

2.51

 Liqu

2.50

 Grad

2.40

�

2.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.