INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.1.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

0:0.10

1:0.09

2:0.08

3:0.06

4:0.08

5:0.09

6:0.08

7:0.07

8:0.06

9:0.06

10:0.07

11:0.10

Negative Logits

 butterflies

-1.41

 Butterfly

-1.40

 Beaut

-1.33

 サーティワン

-1.31

hyde

-1.31

)—

-1.29

 itself

-1.29

vertising

-1.27

 malfunction

-1.26

 Violet

-1.25

POSITIVE LOGITS

yip

1.55

edin

1.43

verning

1.43

Led

1.42

arnaev

1.40

cific

1.34

jen

1.31

irs

1.29

INGS

1.28

Standard

1.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.