INDEX

Explanations

phrases related to financial transactions and payment

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

0:0.09

1:0.02

2:0.17

3:0.08

4:0.09

5:0.05

6:0.02

7:0.02

8:0.23

9:0.12

10:0.04

11:0.02

Negative Logits

 Cells

-1.23

icip

-1.17

xual

-1.11

aiman

-1.11

aspx

-1.08

��

-1.08

structed

-1.08

ierre

-1.07

ucci

-1.07

cluding

-1.06

POSITIVE LOGITS

 royalties

1.58

 dividends

1.49

arations

1.48

 premium

1.42

 upfront

1.39

license

1.38

 subscription

1.36

 dues

1.33

 upkeep

1.28

こ

1.27

Activations Density 0.013%

phrases related to financial transactions and payment

No Comments

No Known Activations