INDEX

Explanations

numeric measurements and specifications

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

0:0.12

1:0.06

2:0.13

3:0.09

4:0.06

5:0.08

6:0.03

7:0.06

8:0.07

9:0.11

10:0.08

11:0.06

Negative Logits

ItemThumbnailImage

-1.83

-1.38

inator

-1.36

Ago

-1.33

ドラゴン

-1.32

activate

-1.29

姫

-1.29

Untitled

-1.28

 Simulator

-1.24

�

-1.23

POSITIVE LOGITS

enegger

1.35

 tolerant

1.32

 willing

1.22

 metric

1.21

ulz

1.20

orthy

1.18

 Calder

1.18

 prison

1.13

 fault

1.13

GUN

1.12

Activations Density 0.024%

numeric measurements and specifications

No Comments

No Known Activations