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

1:0.08

2:0.08

3:0.08

4:0.09

5:0.07

6:0.08

7:0.08

8:0.08

9:0.08

10:0.07

11:0.07

Negative Logits

 Logan

-3.32

 Omega

-3.08

 Olympia

-3.01

 Garry

-2.95

 Vaughan

-2.87

 Salmon

-2.81

 Mayo

-2.78

 Ribbon

-2.67

 Buch

-2.67

XT

-2.64

POSITIVE LOGITS

icut

3.02

abama

3.01

ْ

2.99

weapons

2.96

hower

2.93

civil

2.76

urdue

2.75

Weapons

2.70

ivil

2.69

ebus

2.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.