INDEX

Explanations

elements related to social media interactions and policies

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

0:0.09

1:0.04

2:0.04

3:0.09

4:0.25

5:0.09

6:0.05

7:0.07

8:0.05

9:0.08

10:0.06

11:0.03

Negative Logits

cheon

-2.40

'."

-2.37

)",

-2.33

ufact

-2.28

 Ghana

-2.27

 alot

-2.27

 Telecom

-2.26

hips

-2.22

CTR

-2.21

..."

-2.19

POSITIVE LOGITS

→

2.62

>,

2.45

[/

2.37

</

2.36

 afterlife

2.31

————————————————

2.30

2.15

2.14

 morally

2.13

 conscientious

2.09

Activations Density 0.001%

elements related to social media interactions and policies

No Comments

No Known Activations