INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.1.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

1:0.09

2:0.07

3:0.06

4:0.09

5:0.09

6:0.09

7:0.09

8:0.07

9:0.07

10:0.07

11:0.09

Negative Logits

��

-1.52

iaries

-1.50

mble

-1.42

ebted

-1.38

axter

-1.33

imore

-1.31

Footnote

-1.30

iary

-1.26

edged

-1.22

vest

-1.21

POSITIVE LOGITS

 Biol

1.35

 largeDownload

1.30

 sink

1.26

 Learns

1.24

イト

1.22

MEN

1.21

 appet

1.18

 Dwarf

1.16

%:

1.16

rogens

1.16

Activations Density 0.000%

No Known Activations

This feature has no known activations.