INDEX

Explanations

references to homemade food and drinks or DIY-related terms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.05

1:0.05

2:0.16

3:0.11

4:0.11

5:0.09

6:0.02

7:0.03

8:0.09

9:0.17

10:0.05

11:0.03

Negative Logits

hematically

-1.59

xus

-1.44

forth

-1.38

 Statistical

-1.33

antically

-1.26

HUD

-1.26

 Watson

-1.26

��

-1.24

 Tillerson

-1.23

":"/

-1.21

POSITIVE LOGITS

 hobby

1.46

 accompan

1.39

 kits

1.36

 chore

1.31

Bul

1.29

 decoration

1.29

 arrang

1.26

 carts

1.22

 guide

1.22

 Patch

1.22

Activations Density 0.009%

references to homemade food and drinks or DIY-related terms

No Comments

No Known Activations