INDEX

Explanations

keywords related to movies and their production details

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

0:0.41

1:0.02

2:0.05

3:0.12

4:0.03

5:0.08

6:0.03

7:0.05

8:0.10

9:0.02

10:0.03

11:0.02

Negative Logits

odynam

-2.42

dayName

-2.40

 lapt

-2.38

 roadside

-2.37

�

-2.35

 rust

-2.22

�

-2.21

�

-2.17

 Canberra

-2.17

arat

-2.14

POSITIVE LOGITS

 Animation

3.94

 Studios

3.39

 Avengers

3.28

 Deadpool

3.26

Marvel

3.26

 Comics

3.24

 sequels

3.24

 Marvel

3.19

 superhero

3.11

 cinematic

3.09

Activations Density 0.340%

keywords related to movies and their production details

No Comments

No Known Activations