INDEX

Explanations

words related to analyzing and discussing various situations or phenomena, such as evaluation, performance, opinions, and decisions

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

phrases related to performance and evaluation in various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

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

Head Attr Weights

0:0.01

1:0.11

2:0.06

3:0.04

4:0.01

5:0.04

6:0.06

7:0.06

8:0.06

9:0.06

10:0.07

11:0.38

Negative Logits

 Freak

-1.46

ANN

-1.27

ttes

-1.27

 Vanity

-1.19

 Alive

-1.18

 Popular

-1.15

uploads

-1.14

Newsletter

-1.12

Bus

-1.11

 Polit

-1.11

POSITIVE LOGITS

 weakest

1.44

inth

1.41

rongh

1.36

?'

1.29

alach

1.26

?",

1.25

perty

1.24

adesh

1.23

Nusra

1.23

ungle

1.22

Activations Density 0.128%

words related to analyzing and discussing various situations or phenomena, such as evaluation, performance, opinions, and decisions

phrases related to performance and evaluation in various contexts

No Known Activations

words related to analyzing and discussing various situations or phenomena, such as evaluation, performance, opinions, and decisions

phrases related to performance and evaluation in various contexts

No Known Activations