INDEX

Explanations

instances of specific symbols or characters that might indicate parts of a document layout or navigation

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

1:0.14

2:0.06

3:0.20

4:0.02

5:0.04

6:0.06

7:0.09

8:0.05

9:0.18

10:0.05

11:0.05

Negative Logits

icken

-1.35

onne

-1.34

 abstinence

-1.32

sample

-1.18

arcity

-1.17

 intrins

-1.15

 recip

-1.14

urers

-1.13

 Punk

-1.13

 electors

-1.13

POSITIVE LOGITS

 IMAGES

1.71

yright

1.34

Enlarge

1.32

Pull

1.25

ヴァ

1.23

iership

1.22

 Shutterstock

1.19

isl

1.19

VPN

1.18

||||

1.18

Activations Density 0.002%

instances of specific symbols or characters that might indicate parts of a document layout or navigation

No Comments

No Known Activations