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

1:0.06

2:0.08

3:0.08

4:0.09

5:0.08

6:0.08

7:0.07

8:0.08

9:0.09

10:0.08

11:0.08

Negative Logits

iot

-1.54

 mont

-1.38

>:

-1.38

 nested

-1.37

astern

-1.36

/>

-1.36

 Shroud

-1.35

ono

-1.34

/_

-1.34

 documented

-1.33

POSITIVE LOGITS

 millenn

1.61

�士

1.60

 Doomsday

1.60

 fortunes

1.55

 automakers

1.49

Americans

1.46

 trends

1.41

 Yamaha

1.41

cour

1.40

agna

1.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.