INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.07

1:0.05

2:0.09

3:0.08

4:0.05

5:0.10

6:0.11

7:0.08

8:0.07

9:0.10

10:0.10

11:0.04

Negative Logits

bos

-1.39

ydia

-1.32

 Devi

-1.23

efe

-1.23

escription

-1.22

emi

-1.22

realDonaldTrump

-1.20

ONSORED

-1.19

版

-1.18

AAA

-1.18

POSITIVE LOGITS

Stone

1.34

Mesh

1.34

oute

1.33

Lin

1.31

quartered

1.29

stall

1.25

 Primordial

1.24

Sharp

1.22

press

1.21

Develop

1.20

Activations Density 0.000%

No Known Activations

This feature has no known activations.