INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.08

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.07

9:0.08

10:0.09

11:0.07

Negative Logits

 Renew

-2.68

 Reeves

-2.56

 restoring

-2.37

Wr

-2.31

TA

-2.28

 claw

-2.27

 shaved

-2.25

 Greeks

-2.21

 Zeus

-2.20

 resh

-2.19

POSITIVE LOGITS

��

4.00

3.48

ihar

3.36

SourceFile

3.13

 Cind

2.99

uala

2.96

ijn

2.88

 Rarity

2.83

 Pokémon

2.74

adelphia

2.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.