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

0:0.09

1:0.07

2:0.07

3:0.08

4:0.07

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

 citation

-2.78

 MacArthur

-2.54

 Broadway

-2.48

RECT

-2.31

EXT

-2.30

う

-2.27

append

-2.27

TEXT

-2.26

foot

-2.16

STDOUT

-2.15

POSITIVE LOGITS

odynam

2.63

 indu

2.55

iazep

2.45

 Pupp

2.27

 chall

2.26

 Yanuk

2.24

 chem

2.21

erva

2.21

tics

2.21

Demon

2.19

Activations Density 0.000%

No Known Activations

This feature has no known activations.