INDEX

Explanations

No Explanations Found

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

0:0.08

1:0.08

2:0.06

3:0.08

4:0.08

5:0.07

6:0.10

7:0.07

8:0.09

9:0.06

10:0.09

11:0.10

Negative Logits

livious

-1.50

illary

-1.49

hover

-1.37

shield

-1.35

uyomi

-1.35

 unseen

-1.33

terior

-1.28

hell

-1.28

 conve

-1.25

lez

-1.25

POSITIVE LOGITS

Fif

1.42

NEY

1.34

 developmental

1.30

rupal

1.30

 Mississ

1.29

Track

1.27

abies

1.27

emate

1.25

JM

1.22

BuyableInstoreAndOnline

1.20

Activations Density 0.000%

No Known Activations

This feature has no known activations.