INDEX

Explanations

phrases related to enjoyment and fun activities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

0:0.01

1:0.02

2:0.05

3:0.03

4:0.02

5:0.05

6:0.05

7:0.12

8:0.05

9:0.06

10:0.06

11:0.41

Negative Logits

ortium

-1.70

��

-1.51

pex

-1.49

 defic

-1.49

 dilig

-1.40

yrus

-1.33

ailability

-1.32

 registry

-1.32

pta

-1.30

ascus

-1.28

POSITIVE LOGITS

Reviewer

1.55

 trivia

1.47

 playground

1.31

 salsa

1.29

 Monkey

1.26

 scen

1.24

mire

1.24

Angelo

1.23

 comedy

1.22

 Lyndon

1.20

Activations Density 0.045%

phrases related to enjoyment and fun activities

No Comments

No Known Activations