INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.06

2:0.08

3:0.09

4:0.09

5:0.09

6:0.07

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

esters

-1.58

 Bonds

-1.57

�

-1.55

esta

-1.49

alsa

-1.48

 hybrids

-1.45

 Centauri

-1.45

NG

-1.43

 Prol

-1.43

aida

-1.41

POSITIVE LOGITS

 tolerance

1.57

upt

1.56

 pedoph

1.50

zen

1.43

rid

1.42

lando

1.40

 correct

1.40

 values

1.39

?"

1.38

mA

1.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.