INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

2:0.08

3:0.08

4:0.08

5:0.07

6:0.07

7:0.08

8:0.07

9:0.07

10:0.09

11:0.09

Negative Logits

 Michaels

-3.22

OTOS

-3.19

oxide

-2.96

 Andrews

-2.95

ioxide

-2.88

 bruising

-2.86

osite

-2.75

 Aviation

-2.63

oward

-2.62

 Chemical

-2.60

POSITIVE LOGITS

 denomin

2.80

神

2.68

 Advent

2.61

 DISTR

2.51

 disenfranch

2.49

BIP

2.45

uler

2.40

ヴ

2.38

Cal

2.36

 glim

2.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.