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

5:0.09

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 Moonlight

-3.84

 Centauri

-3.15

 Parker

-3.13

 Spurs

-2.85

 Compton

-2.85

 Sund

-2.84

Spot

-2.81

 Hayward

-2.68

 BART

-2.65

 Clippers

-2.64

POSITIVE LOGITS

ahon

3.00

 Healthcare

2.81

Health

2.71

 EntityItem

2.67

irm

2.63

 insure

2.62

irming

2.62

health

2.52

ateg

2.42

 stret

2.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.