INDEX

Explanations

details related to competitive gaming and events

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

0:0.15

1:0.02

2:0.08

3:0.09

4:0.03

5:0.05

6:0.06

7:0.06

8:0.31

9:0.04

10:0.02

11:0.04

Negative Logits

 Afghans

-3.58

 Scientology

-3.53

 Kabul

-3.49

 Hubbard

-3.42

 Scient

-3.42

 Afghan

-3.40

adh

-3.35

 envis

-3.27

 Gaul

-3.24

 Kund

-3.19

POSITIVE LOGITS

 Brawl

7.26

 Smash

7.21

 Melee

6.64

 Yoshi

5.71

 Bowser

5.36

 Pikachu

4.80

 Peach

4.71

Wii

4.65

 Twitch

4.58

 Donkey

4.55

Activations Density 0.008%

details related to competitive gaming and events

No Comments

No Known Activations