INDEX

Explanations

instances of numerical data and their relation to potential conflicts or agreements

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

0:0.03

1:0.04

2:0.04

3:0.10

4:0.03

5:0.11

6:0.03

7:0.41

8:0.08

9:0.03

10:0.03

11:0.03

Negative Logits

ertodd

-2.84

worms

-2.56

esome

-2.52

nsic

-2.49

ecause

-2.35

worm

-2.30

zsche

-2.21

inders

-2.21

amaru

-2.19

catentry

-2.19

POSITIVE LOGITS

 Americans

2.79

 American

2.62

 homegrown

2.61

 Americas

2.57

USA

2.56

 America

2.52

 AMER

2.51

 Luxem

2.50

USA

2.50

 Baltic

2.42

Activations Density 0.101%

instances of numerical data and their relation to potential conflicts or agreements

No Comments

No Known Activations