INDEX

Explanations

phrases related to calls to action or requests for engagement

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

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

0:0.03

1:0.04

2:0.13

3:0.10

4:0.12

5:0.05

6:0.05

7:0.03

8:0.07

9:0.05

10:0.18

11:0.10

Negative Logits

 metabol

-1.47

agonist

-1.39

 perce

-1.33

 habit

-1.33

vas

-1.29

 deceived

-1.26

 hooked

-1.26

 differently

-1.24

ocally

-1.24

 perceived

-1.23

POSITIVE LOGITS

DragonMagazine

1.71

Topics

1.69

taboola

1.61

Sources

1.44

Information

1.40

Visit

1.35

Credits

1.34

please

1.34

reon

1.32

 gloss

1.31

Activations Density 0.015%

phrases related to calls to action or requests for engagement

No Comments

No Known Activations