INDEX

Explanations

phrases related to music studios and sound production

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.14

1:0.05

2:0.08

3:0.05

4:0.04

5:0.02

6:0.21

7:0.14

8:0.01

9:0.03

10:0.07

11:0.09

Negative Logits

wal

-2.84

 deterrence

-2.55

Saf

-2.44

 Khal

-2.42

Wal

-2.39

 milit

-2.33

Kyr

-2.31

 overth

-2.29

 repealed

-2.28

 shaming

-2.28

POSITIVE LOGITS

 Studio

6.69

Studio

6.29

 studio

6.07

 studios

5.65

 Studios

4.71

 Producer

4.05

 Artists

3.77

 workspace

3.57

stud

3.52

 producer

3.45

Activations Density 0.022%

phrases related to music studios and sound production

No Comments

No Known Activations