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

0:0.09

1:0.09

2:0.07

3:0.08

4:0.08

5:0.07

6:0.07

7:0.08

8:0.08

9:0.08

10:0.06

11:0.08

Negative Logits

rontal

-2.92

Bin

-2.87

displayText

-2.63

 Commit

-2.56

 Archdemon

-2.51

 Insp

-2.51

 workspace

-2.45

 cursor

-2.44

Khe

-2.43

 bricks

-2.37

POSITIVE LOGITS

Ireland

2.66

 Rory

2.58

 Roth

2.46

Length

2.42

 estates

2.42

France

2.37

Mae

2.37

 Daly

2.36

 Warren

2.35

 Switzerland

2.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.