INDEX

Explanations

expressions of gratitude and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

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

0:0.08

1:0.06

2:0.07

3:0.08

4:0.03

5:0.07

6:0.06

7:0.04

8:0.15

9:0.17

10:0.10

11:0.03

Negative Logits

soDeliveryDate

-1.81

 favoured

-1.23

 mutated

-1.18

 triv

-1.14

Downloadha

-1.13

umes

-1.12

 arsen

-1.11

 identical

-1.10

 maps

-1.09

=(

-1.09

POSITIVE LOGITS

ipeg

1.46

 blessings

1.41

 generosity

1.32

 gifts

1.32

 thanked

1.30

Brave

1.29

 Sierra

1.25

 kindness

1.23

Thank

1.22

 gratitude

1.19

Activations Density 0.010%

expressions of gratitude and appreciation

No Comments

No Known Activations