INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

2:0.07

3:0.08

4:0.08

5:0.08

6:0.08

7:0.09

8:0.06

9:0.08

10:0.09

11:0.08

Negative Logits

DOS

-3.43

maxwell

-2.99

ERN

-2.63

yang

-2.61

vind

-2.60

Greek

-2.60

addin

-2.59

IPS

-2.58

onse

-2.57

arus

-2.55

POSITIVE LOGITS

 roundup

2.79

 Rent

2.60

 rental

2.57

 Halls

2.39

 Majesty

2.39

 jurisdiction

2.36

 Fisher

2.36

 answers

2.35

 quotation

2.33

 Price

2.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.