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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.08

2:0.08

3:0.09

4:0.08

5:0.08

6:0.07

7:0.09

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

cffffcc

-2.62

›

-2.43

 Issues

-2.35

 Respond

-2.34

etermined

-2.32

itiz

-2.26

etermin

-2.25

 Sutherland

-2.24

 embr

-2.24

 resolving

-2.23

POSITIVE LOGITS

peat

2.95

 Mafia

2.65

 Georgian

2.61

 mafia

2.59

 monarchy

2.53

 Kyoto

2.46

beat

2.39

NRS

2.38

atin

2.30

 Byzantine

2.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.