INDEX

Explanations

terms related to gaming features, improvements, and match management systems

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

0:0.15

1:0.06

2:0.04

3:0.09

4:0.05

5:0.01

6:0.22

7:0.12

8:0.02

9:0.03

10:0.05

11:0.09

Negative Logits

 ALEC

-3.37

覚醒

-3.12

 Tyrann

-2.94

 Legisl

-2.90

 Carney

-2.87

 Cuomo

-2.87

 Palin

-2.85

 Jindal

-2.68

 Livingston

-2.60

 Labrador

-2.58

POSITIVE LOGITS

 match

7.39

Match

7.24

 Match

7.20

 matches

7.15

match

6.79

 matched

4.62

 tournament

4.43

 esports

4.42

 eSports

4.26

 Dota

4.16

Activations Density 0.067%

terms related to gaming features, improvements, and match management systems

No Comments

No Known Activations