INDEX

Explanations

phrases indicating complexity or detail 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_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

0:0.24

1:0.06

2:0.14

3:0.11

4:0.06

5:0.05

6:0.05

7:0.05

8:0.08

9:0.02

10:0.06

11:0.03

Negative Logits

 rall

-1.33

 trainers

-1.30

 helicop

-1.28

 trainer

-1.28

 horizont

-1.26

cas

-1.22

 containment

-1.21

rul

-1.21

ガ

-1.20

 advent

-1.19

POSITIVE LOGITS

 Marketable

1.66

%"

1.56

externalActionCode

1.42

selves

1.41

 guiName

1.37

 guiActiveUn

1.34

Dow

1.32

 Coffin

1.27

��

1.21

 Certainly

1.20

Activations Density 0.085%

phrases indicating complexity or detail in narratives

No Comments

No Known Activations