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

1:0.07

2:0.07

3:0.08

4:0.07

5:0.07

6:0.08

7:0.08

8:0.09

9:0.08

10:0.09

11:0.09

Negative Logits

 sabot

-1.34

cms

-1.33

 HELL

-1.30

 incarcer

-1.28

archives

-1.27

 Argent

-1.27

merce

-1.26

 apprehend

-1.25

 investigating

-1.21

ateurs

-1.21

POSITIVE LOGITS

�

1.48

Jump

1.47

ケ

1.45

JV

1.37

Lic

1.34

••

1.34

imeo

1.33

Jen

1.33

Sequ

1.30

ciating

1.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.