INDEX

Explanations

phrases related to financial transactions or investments

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

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

0:0.06

1:0.02

2:0.13

3:0.07

4:0.07

5:0.19

6:0.02

7:0.05

8:0.05

9:0.18

10:0.06

11:0.04

Negative Logits

ウス

-1.21

Ga

-1.14

iste

-1.14

ァ

-1.11

 Eggs

-1.10

enment

-1.10

 Klopp

-1.10

eus

-1.08

ゴン

-1.08

ities

-1.06

POSITIVE LOGITS

tax

1.47

mercial

1.44

USD

1.37

 payable

1.31

aundering

1.30

tax

1.30

total

1.27

=$

1.26

 invested

1.21

 taxes

1.20

Activations Density 0.031%

phrases related to financial transactions or investments

No Comments

No Known Activations