INDEX

Explanations

interrogative words and phrases, particularly questions or inquiries

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

2:0.12

3:0.13

4:0.01

5:0.03

6:0.04

7:0.10

8:0.06

9:0.19

10:0.10

11:0.13

Negative Logits

hement

-1.41

eries

-1.34

geoning

-1.32

uably

-1.30

vir

-1.28

renched

-1.25

alia

-1.19

raught

-1.18

pmwiki

-1.17

rolled

-1.17

POSITIVE LOGITS

 anymore

1.50

 behavi

1.29

 newsp

1.24

 terminology

1.23

 myself

1.22

nor

1.16

 whereabouts

1.15

 Palestin

1.15

 explan

1.12

 Doodle

1.11

Activations Density 0.033%

interrogative words and phrases, particularly questions or inquiries

No Comments

No Known Activations