INDEX

Explanations

users commenting on and experiencing amusing situations related to social interactions and nightlife

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

instances of sarcasm or sarcastic remarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

1:0.03

2:0.17

3:0.05

4:0.19

5:0.09

6:0.03

7:0.03

8:0.07

9:0.14

10:0.06

11:0.03

Negative Logits

 forc

-1.23

 cryst

-1.22

uckland

-1.17

 arsen

-1.16

 coerc

-1.13

listed

-1.11

 negro

-1.09

 legally

-1.07

 occas

-1.07

 leases

-1.07

POSITIVE LOGITS

 Imaging

1.25

 disappointment

1.25

 Tears

1.24

 Bastard

1.22

SHIP

1.22

 Reson

1.21

 Satisf

1.20

 envy

1.19

 Cyber

1.19

 Doomsday

1.18

Activations Density 0.002%

users commenting on and experiencing amusing situations related to social interactions and nightlife

instances of sarcasm or sarcastic remarks

No Comments

No Known Activations