INDEX

Explanations

references to financial and economic terms related to capital, investment, and business

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

terms and phrases related to capital investment and financing

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

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

Head Attr Weights

0:0.06

1:0.05

2:0.19

3:0.11

4:0.05

5:0.06

6:0.03

7:0.05

8:0.05

9:0.21

10:0.06

11:0.03

Negative Logits

 incrim

-1.54

 inconsistency

-1.36

mallow

-1.34

ewitness

-1.34

ITNESS

-1.24

erb

-1.20

 compe

-1.18

pathy

-1.17

CHR

-1.15

essage

-1.15

POSITIVE LOGITS

istan

1.37

 financed

1.25

 Ventures

1.24

 Alas

1.19

 financing

1.17

omics

1.17

(£

1.16

 Meridian

1.13

デ

1.12

raising

1.10

Activations Density 0.026%

references to financial and economic terms related to capital, investment, and business

terms and phrases related to capital investment and financing

No Known Activations