INDEX

Explanations

phrases indicating transitions or changes in state or position

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_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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.04

1:0.02

2:0.13

3:0.03

4:0.31

5:0.04

6:0.02

7:0.02

8:0.21

9:0.08

10:0.04

11:0.01

Negative Logits

 teasp

-1.42

pecially

-1.39

UFF

-1.33

Truth

-1.28

Nap

-1.25

bleacher

-1.24

Warning

-1.23

vale

-1.22

psons

-1.21

MN

-1.21

POSITIVE LOGITS

phase

1.33

 smoothly

1.33

HDR

1.33

 turnaround

1.30

 heights

1.28

 groove

1.26

DEN

1.25

 Centauri

1.25

ophys

1.25

 Shine

1.24

Activations Density 0.005%

phrases indicating transitions or changes in state or position

No Comments

No Known Activations