INDEX

Explanations

promotional offers related to subscriptions

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.01

1:0.01

2:0.15

3:0.15

4:0.07

5:0.02

6:0.06

7:0.10

8:0.05

9:0.05

10:0.15

11:0.12

Negative Logits

teness

-1.56

omorphic

-1.40

ilts

-1.38

viation

-1.38

matter

-1.35

omon

-1.34

 regress

-1.32

livious

-1.30

conom

-1.30

yrus

-1.29

POSITIVE LOGITS

taboola

1.37

Ble

1.33

Subscribe

1.33

 celeb

1.32

 Trash

1.30

 Visit

1.29

 Help

1.26

 Socialist

1.24

$$$$

1.23

 Subscribe

1.23

Activations Density 0.001%

promotional offers related to subscriptions

No Comments

No Known Activations