INDEX

Explanations

terms and phrases associated with coding and data frameworks

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

0:0.05

1:0.02

2:0.03

3:0.20

4:0.06

5:0.10

6:0.03

7:0.09

8:0.04

9:0.03

10:0.17

11:0.13

Negative Logits

,'"

-2.95

,'

-2.68

',"

-2.39

],"

-2.34

.'"

-2.31

 notwithstanding

-2.27

 nationally

-2.23

],[

-2.20

:'

-2.19

 seldom

-2.16

POSITIVE LOGITS

anco

2.65

ieu

2.54

wik

2.54

uay

2.52

gra

2.41

yk

2.40

ozo

2.39

uca

2.38

uka

2.38

duino

2.37

Activations Density 0.004%

terms and phrases associated with coding and data frameworks

No Comments

No Known Activations