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

0:0.07

1:0.08

2:0.08

3:0.07

4:0.08

5:0.09

6:0.07

7:0.08

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

���

-1.73

aur

-1.52

sue

-1.51

 destro

-1.49

OPLE

-1.49

 migrate

-1.48

 starve

-1.44

 Learns

-1.44

 skelet

-1.42

 agre

-1.40

POSITIVE LOGITS

efficients

1.52

ificate

1.51

nit

1.50

xt

1.43

arnaev

1.39

caliber

1.39

 Waterloo

1.39

 Quentin

1.39

renheit

1.38

pan

1.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.