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

2:0.09

3:0.08

4:0.08

5:0.08

6:0.08

7:0.09

8:0.07

9:0.08

10:0.09

11:0.07

Negative Logits

 Serbia

-2.79

amaz

-2.68

ICO

-2.48

 Trad

-2.43

 Fighting

-2.42

 Invention

-2.40

itant

-2.40

 Stru

-2.40

 Serbian

-2.39

Muk

-2.38

POSITIVE LOGITS

 invade

2.84

 occupant

2.82

 unlock

2.65

 retrie

2.65

NetMessage

2.63

 intr

2.43

 occupying

2.40

 plush

2.35

 overw

2.30

 intrusive

2.30

Activations Density 0.000%

No Known Activations

This feature has no known activations.