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

1:0.07

2:0.07

3:0.08

4:0.08

5:0.08

6:0.08

7:0.06

8:0.09

9:0.10

10:0.08

11:0.07

Negative Logits

osis

-3.34

Whe

-2.82

eph

-2.82

por

-2.81

Ach

-2.71

IPS

-2.67

 Shawn

-2.67

phe

-2.66

Pont

-2.64

adelphia

-2.63

POSITIVE LOGITS

 Stevenson

2.95

 utilitarian

2.56

 derog

2.52

 realism

2.46

xual

2.34

 reader

2.33

 firefighter

2.32

 readers

2.29

 deflation

2.29

 Tolkien

2.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.