INDEX

Explanations

references to specific smartphone models, particularly the Nokia Lumia series

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

0:0.03

1:0.03

2:0.04

3:0.03

4:0.03

5:0.04

6:0.24

7:0.16

8:0.03

9:0.05

10:0.18

11:0.09

Negative Logits

 Flavoring

-1.45

 Sabb

-1.38

 fals

-1.35

 bribes

-1.33

 stringent

-1.32

 scrut

-1.29

 Scientology

-1.28

 disqual

-1.26

 seminars

-1.26

 strict

-1.24

POSITIVE LOGITS

xxx

1.35

aver

1.29

 Anniversary

1.28

claimed

1.26

ager

1.23

acy

1.23

roxy

1.23

near

1.22

 Shots

1.22

emp

1.20

Activations Density 0.001%

references to specific smartphone models, particularly the Nokia Lumia series

No Comments

No Known Activations