INDEX

Explanations

financial and monetary terms related to credit, repayment, and business

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

2:0.11

3:0.10

4:0.05

5:0.11

6:0.02

7:0.02

8:0.21

9:0.17

10:0.05

11:0.03

Negative Logits

 Digest

-1.31

uploads

-1.20

ˈ

-1.06

Frames

-1.04

taboola

-1.00

ertodd

-0.98

SELECT

-0.97

 mashed

-0.96

 icing

-0.95

 microw

-0.94

POSITIVE LOGITS

lyak

1.20

autions

1.18

armac

1.18

ALSE

1.16

enary

1.11

osen

1.09

ICA

1.08

itional

1.04

Ou

1.03

zeb

1.01

Activations Density 0.038%

financial and monetary terms related to credit, repayment, and business

No Comments

No Known Activations