INDEX

Explanations

references to email verification and subscription processes

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

0:0.03

1:0.02

2:0.04

3:0.06

4:0.12

5:0.37

6:0.03

7:0.04

8:0.12

9:0.05

10:0.03

11:0.03

Negative Logits

 whereas

-3.21

 whilst

-3.12

 while

-3.07

 till

-3.04

 until

-2.83

 brunt

-2.81

 rather

-2.80

 thru

-2.79

 notwithstanding

-2.51

 since

-2.51

POSITIVE LOGITS

moil

2.76

idel

2.74

shall

2.53

gdala

2.49

Attach

2.42

ucker

2.37

isol

2.35

aram

2.34

ELF

2.33

You

2.32

Activations Density 0.006%

references to email verification and subscription processes

No Comments

No Known Activations