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

1:0.09

2:0.08

3:0.08

4:0.08

5:0.07

6:0.07

7:0.09

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

 Nasa

-2.76

 Hermes

-2.69

 Armstrong

-2.64

weather

-2.58

 wear

-2.46

Rih

-2.42

 Gear

-2.41

 Einstein

-2.38

 McKenzie

-2.37

Gear

-2.36

POSITIVE LOGITS

覚醒

3.09

PAL

2.87

 princ

2.86

raltar

2.86

 Hispan

2.84

ł

2.82

 Puerto

2.78

razil

2.74

odore

2.67

retty

2.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.