INDEX

Explanations

phrases that indicate significant improvements or advancements

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

1:0.04

2:0.06

3:0.05

4:0.01

5:0.04

6:0.04

7:0.06

8:0.06

9:0.43

10:0.06

11:0.08

Negative Logits

stress

-1.28

 childbirth

-1.26

offic

-1.25

speak

-1.24

chool

-1.23

ago

-1.20

epend

-1.18

ebook

-1.18

velt

-1.17

rom

-1.16

POSITIVE LOGITS

inav

1.41

ADRA

1.37

vil

1.36

rahim

1.33

inness

1.28

inas

1.26

="#

1.25

 dividing

1.22

orical

1.21

ZI

1.20

Activations Density 0.041%

phrases that indicate significant improvements or advancements

No Comments

No Known Activations