INDEX

Explanations

relationships and characteristics of individuals, particularly focusing on physical attributes and roles in narratives

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

1:0.06

2:0.03

3:0.03

4:0.06

5:0.02

6:0.03

7:0.40

8:0.02

9:0.04

10:0.03

11:0.16

Negative Logits

 Eagle

-2.28

yd

-2.27

Zup

-2.21

Eye

-2.20

 Eagles

-2.15

ACE

-2.13

embed

-2.13

 commod

-2.13

EE

-2.12

 Turtles

-2.11

POSITIVE LOGITS

Hung

2.58

por

2.36

artney

2.31

ascus

2.26

pur

2.20

 Stalin

2.19

urg

2.18

 Parliament

2.13

chel

2.11

 Pierre

2.10

Activations Density 0.015%

relationships and characteristics of individuals, particularly focusing on physical attributes and roles in narratives

No Comments

No Known Activations