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

0:0.08

1:0.07

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

 informants

-2.61

 Malays

-2.44

 slit

-2.39

 Hindi

-2.38

 reader

-2.38

 lantern

-2.37

velength

-2.35

 Jane

-2.35

 trunc

-2.35

Tube

-2.31

POSITIVE LOGITS

alky

2.85

aq

2.81

auer

2.69

aurus

2.68

 Arena

2.68

 Aber

2.63

mur

2.60

 Cardinals

2.56

AZ

2.52

uve

2.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.