INDEX

Explanations

references to laws and legal actions, particularly those pertaining to civil rights and discrimination

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

0:0.02

1:0.01

2:0.08

3:0.07

4:0.13

5:0.03

6:0.03

7:0.31

8:0.03

9:0.03

10:0.11

11:0.10

Negative Logits

sic

-1.66

 toget

-1.65

 Thumbnails

-1.64

estern

-1.63

-1.57

entimes

-1.56

ebook

-1.53

esville

-1.51

rows

-1.45

rio

-1.45

POSITIVE LOGITS

 rule

1.48

-+-+

1.44

 unanimously

1.42

 Codes

1.41

Naj

1.39

 bans

1.36

 Rule

1.33

 regulations

1.33

 distinctions

1.32

 ordinances

1.31

Activations Density 0.002%

references to laws and legal actions, particularly those pertaining to civil rights and discrimination

No Comments

No Known Activations