INDEX

Explanations

data related to various types of achievements or statuses across different fields

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

information related to statistical data or rankings on rarity

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.07

1:0.05

2:0.08

3:0.15

4:0.05

5:0.10

6:0.04

7:0.03

8:0.19

9:0.11

10:0.07

11:0.02

Negative Logits

��

-1.60

isi

-1.23

zik

-1.21

RAW

-1.21

uers

-1.15

EGIN

-1.12

��

-1.11

��

-1.11

aleb

-1.10

��

-1.10

POSITIVE LOGITS

 polled

1.24

etheless

1.12

 excluding

1.06

pees

1.05

Vs

1.05

 overall

1.04

 Moody

1.03

 Mania

1.02

 rapes

1.01

Activations Density 0.103%

data related to various types of achievements or statuses across different fields

information related to statistical data or rankings on rarity

No Comments

No Known Activations