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

4:0.07

5:0.08

6:0.07

7:0.09

8:0.08

9:0.09

10:0.07

11:0.09

Negative Logits

 Zoro

-3.28

Khe

-3.17

 Syri

-3.02

 Shinra

-2.96

 synagogue

-2.91

 Jakarta

-2.88

 Mana

-2.83

 Erit

-2.79

Elf

-2.79

Elf

-2.78

POSITIVE LOGITS

 airflow

2.61

 litigation

2.59

��

2.50

gate

2.48

 Excellence

2.46

 advers

2.44

 rigorous

2.38

 prod

2.38

 advanced

2.32

urated

2.31

Activations Density 0.000%

No Known Activations

This feature has no known activations.