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

0:0.08

1:0.07

2:0.07

3:0.08

4:0.08

5:0.08

6:0.08

7:0.06

8:0.09

9:0.09

10:0.08

11:0.08

Negative Logits

Sov

-1.44

 typew

-1.38

 Sally

-1.31

 inacc

-1.26

utra

-1.25

 rehe

-1.23

Downloadha

-1.22

Wikipedia

-1.19

Repe

-1.19

 clerks

-1.16

POSITIVE LOGITS

oor

1.31

kind

1.30

strate

1.30

 dign

1.30

viron

1.29

stars

1.28

acly

1.28

inge

1.28

zzy

1.27

ulent

1.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.