INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

2:0.09

3:0.09

4:0.09

5:0.08

6:0.08

7:0.07

8:0.07

9:0.07

10:0.07

11:0.08

Negative Logits

 volt

-1.55

VAT

-1.49

 elect

-1.46

Downloadha

-1.40

 decom

-1.35

 migrating

-1.35

anson

-1.35

acet

-1.34

loading

-1.33

ect

-1.32

POSITIVE LOGITS

ゴン

2.20

�士

1.68

ِ

1.49

ْ

1.43

��極

1.41

 Answers

1.41

��

1.39

 Stadium

1.39

 curses

1.38

ש

1.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.