INDEX

Explanations

mentions of technology and technical terms such as specific energy storage methods and computer-related terms

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

2:0.08

3:0.16

4:0.03

5:0.21

6:0.03

7:0.02

8:0.16

9:0.14

10:0.03

11:0.02

Negative Logits

ォ

-1.57

Developer

-1.50

ère

-1.50

\\\\\\\\

-1.44

ascript

-1.37

veyard

-1.37

アル

-1.36

 Defeat

-1.33

enegger

-1.28

prises

-1.26

POSITIVE LOGITS

 wise

1.28

 impression

1.20

handed

1.17

 susceptible

1.17

Ung

1.16

sing

1.16

 supp

1.12

 wiser

1.12

 silent

1.12

worthy

1.12

Activations Density 0.167%

mentions of technology and technical terms such as specific energy storage methods and computer-related terms

No Comments

No Known Activations