INDEX

Explanations

terms related to various contexts of "grey" or "gray" areas and their implications

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

0:0.06

1:0.03

2:0.28

3:0.08

4:0.13

5:0.05

6:0.02

7:0.03

8:0.05

9:0.13

10:0.05

11:0.02

Negative Logits

PDATE

-1.59

ghazi

-1.42

cknow

-1.41

GGGGGGGG

-1.38

ーティ

-1.34

Supported

-1.33

cknowled

-1.32

actionDate

-1.30

ァ

-1.28

EMA

-1.27

POSITIVE LOGITS

orc

1.36

road

1.32

 respawn

1.30

 clut

1.29

antha

1.26

 blot

1.23

oak

1.20

ovych

1.18

 decom

1.18

bour

1.15

Activations Density 0.007%

terms related to various contexts of "grey" or "gray" areas and their implications

No Comments

No Known Activations