INDEX

Explanations

contact information details in the text, including email addresses and phone numbers

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

contact information and links for further inquiries or communication

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.06

2:0.09

3:0.08

4:0.04

5:0.08

6:0.06

7:0.06

8:0.07

9:0.12

10:0.14

11:0.05

Negative Logits

 crossover

-1.45

 cater

-1.25

 pump

-1.24

 sucking

-1.21

 instinctively

-1.19

manship

-1.18

 protagonists

-1.17

 pumping

-1.17

 bashing

-1.16

 Canaver

-1.15

POSITIVE LOGITS

quickShipAvailable

1.65

ipel

1.51

Fax

1.48

 srfAttach

1.41

wald

1.37

eton

1.35

dylib

1.35

 tradem

1.34

endix

1.34

itime

1.33

Activations Density 0.106%

contact information details in the text, including email addresses and phone numbers

contact information and links for further inquiries or communication

No Comments

No Known Activations