INDEX

Explanations

character attributes related to friendliness and approachability

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

0:0.12

1:0.03

2:0.20

3:0.19

4:0.03

5:0.11

6:0.02

7:0.07

8:0.04

9:0.02

10:0.10

11:0.02

Negative Logits

 Destination

-2.38

版

-2.36

osate

-2.33

 reopened

-2.30

UPDATE

-2.24

 UPDATE

-2.16

 aborted

-2.16

versible

-2.14

Pwr

-2.12

 closure

-2.12

POSITIVE LOGITS

 temperament

3.52

 demeanor

3.43

 cheerful

3.41

 charming

3.37

 witty

3.22

 arrogant

3.20

 polite

3.17

 charisma

3.17

 charismatic

3.16

 eccentric

3.13

Activations Density 0.878%

character attributes related to friendliness and approachability

No Comments

No Known Activations