INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.1.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

1:0.09

2:0.06

3:0.05

4:0.05

5:0.15

6:0.07

7:0.08

8:0.06

9:0.06

10:0.06

11:0.11

Negative Logits

baugh

-2.05

Mex

-1.54

APH

-1.52

 Department

-1.52

ean

-1.50

essors

-1.42

Ald

-1.42

 Austin

-1.41

�

-1.41

Office

-1.40

POSITIVE LOGITS

��

1.99

etheless

1.98

userc

1.93

 captcha

1.85

othal

1.81

 sorcery

1.67

 exha

1.65

netflix

1.65

 compr

1.61

yip

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.