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

0:0.06

1:0.07

2:0.08

3:0.08

4:0.10

5:0.07

6:0.09

7:0.08

8:0.07

9:0.09

10:0.07

11:0.08

Negative Logits

 Stab

-3.25

 Drugs

-3.07

Wiz

-3.00

 Benz

-2.96

Dud

-2.90

bush

-2.84

Benz

-2.83

 Weed

-2.79

owitz

-2.75

Sax

-2.71

POSITIVE LOGITS

 squid

3.16

 scrolling

3.10

 convol

3.02

 duplication

2.99

 casc

2.92

 relocation

2.90

 cloning

2.89

 processor

2.83

 incorpor

2.82

ixel

2.80

Activations Density 0.000%

No Known Activations

This feature has no known activations.