INDEX

Explanations

themes and patterns in popular song titles and lyrics

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

0:0.06

1:0.02

2:0.04

3:0.48

4:0.04

5:0.09

6:0.02

7:0.05

8:0.03

9:0.02

10:0.07

11:0.03

Negative Logits

 positioning

-2.67

 intensive

-2.62

 regulatory

-2.61

 logistical

-2.57

 prepar

-2.54

 coordinate

-2.52

 mitigation

-2.44

 advisory

-2.42

 mapping

-2.40

 scaling

-2.39

POSITIVE LOGITS

 Colors

3.24

 Trees

3.23

 Machines

3.00

 Enemy

2.95

 Ones

2.94

 Pieces

2.94

 Shoes

2.92

 Happiness

2.91

 Clouds

2.88

 Ships

2.87

Activations Density 0.622%

themes and patterns in popular song titles and lyrics

No Comments

No Known Activations