INDEX

Explanations

phrases indicating the existence of something and its characteristics or qualities

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

0:0.01

1:0.00

2:0.11

3:0.06

4:0.14

5:0.02

6:0.38

7:0.04

8:0.02

9:0.04

10:0.07

11:0.04

Negative Logits

Privacy

-1.28

 Retirement

-1.17

NEY

-1.13

 Leader

-1.13

quest

-1.12

-1.11

 Lauder

-1.11

brance

-1.09

Leader

-1.09

Player

-1.08

POSITIVE LOGITS

theless

1.29

ju

1.28

handedly

1.27

etheless

1.26

inches

1.26

ographed

1.24

undred

1.24

ofer

1.19

paio

1.18

 favourites

1.18

Activations Density 0.011%

phrases indicating the existence of something and its characteristics or qualities

No Comments

No Known Activations