INDEX

Explanations

characters or symbols from various languages

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

symbols and characters commonly used in text

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.03

1:0.05

2:0.10

3:0.25

4:0.03

5:0.03

6:0.08

7:0.14

8:0.06

9:0.06

10:0.06

11:0.06

Negative Logits

ornings

-1.23

 redes

-1.22

acers

-1.18

 excel

-1.09

RIPT

-1.09

 Akin

-1.08

repe

-1.06

 tales

-1.06

laz

-1.05

 Journey

-1.03

POSITIVE LOGITS

wagen

1.50

 unfocusedRange

1.42

henko

1.31

cit

1.29

bilt

1.29

 acid

1.26

apons

1.23

apon

1.22

achev

1.20

heimer

1.18

Activations Density 0.001%

characters or symbols from various languages

symbols and characters commonly used in text

No Comments

No Known Activations