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

1:0.07

2:0.08

3:0.08

4:0.08

5:0.10

6:0.06

7:0.07

8:0.07

9:0.08

10:0.09

11:0.08

Negative Logits

 ancest

-1.35

dro

-1.33

umber

-1.33

digit

-1.29

 territory

-1.27

idine

-1.27

oup

-1.25

uv

-1.24

plet

-1.24

rouse

-1.23

POSITIVE LOGITS

Reviewer

1.40

ィ

1.30

taboola

1.30

 Huawei

1.29

 Nadu

1.29

 Yamaha

1.28

 Stellar

1.26

 Dynamics

1.26

BIT

1.25

actionDate

1.22

Activations Density 0.000%

No Known Activations

This feature has no known activations.