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

2:0.08

3:0.08

4:0.07

5:0.08

6:0.09

7:0.09

8:0.07

9:0.07

10:0.09

11:0.07

Negative Logits

paio

-2.95

hen

-2.81

 eleph

-2.67

 goose

-2.63

 colonel

-2.60

 srfAttach

-2.56

 oxygen

-2.55

 gravy

-2.55

 unbeliev

-2.55

gal

-2.53

POSITIVE LOGITS

 Halifax

2.72

 Carib

2.60

Nas

2.59

Ac

2.55

 Ninth

2.53

 Publishing

2.51

casters

2.50

 Orig

2.49

 dispensary

2.48

 Kobe

2.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.