INDEX

Explanations

phrases related to saving time and reducing effort in 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_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

0:0.02

1:0.03

2:0.08

3:0.18

4:0.02

5:0.04

6:0.07

7:0.12

8:0.05

9:0.18

10:0.06

11:0.09

Negative Logits

istar

-1.36

 motives

-1.29

aph

-1.17

stem

-1.14

SPONSORED

-1.12

osi

-1.11

atham

-1.10

wagon

-1.10

armac

-1.10

urnal

-1.09

POSITIVE LOGITS

anwhile

1.42

 Browse

1.37

 Calories

1.26

 Browser

1.25

 IMAGES

1.23

 readable

1.21

 Collections

1.21

 formatted

1.19

 annotations

1.18

 PowerPoint

1.17

Activations Density 0.010%

phrases related to saving time and reducing effort in processes

No Comments

No Known Activations