INDEX

Explanations

phrases related to competition and participation in sports

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.02

1:0.01

2:0.05

3:0.06

4:0.18

5:0.03

6:0.03

7:0.26

8:0.03

9:0.06

10:0.11

11:0.10

Negative Logits

zanne

-1.64

tarians

-1.59

Nazis

-1.53

odka

-1.52

 hypoc

-1.48

 therap

-1.45

 informants

-1.42

ombs

-1.42

cedented

-1.39

enfranch

-1.38

POSITIVE LOGITS

XIV

1.43

LX

1.41

 Jupiter

1.41

Nat

1.37

 Williamson

1.35

STL

1.32

 Watkins

1.30

Merit

1.30

XVI

1.29

XL

1.27

Activations Density 0.000%

phrases related to competition and participation in sports

No Comments

No Known Activations