INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.08

1:0.08

2:0.08

3:0.07

4:0.09

5:0.08

6:0.09

7:0.07

8:0.08

9:0.09

10:0.07

11:0.08

Negative Logits

rior

-2.45

inguishable

-2.44

 Broadcasting

-2.39

 Metatron

-2.33

gard

-2.33

 Venom

-2.31

ateurs

-2.29

film

-2.29

rint

-2.29

manship

-2.26

POSITIVE LOGITS

 Olympia

2.75

Ire

2.69

Sov

2.67

 Redmond

2.56

euro

2.53

Els

2.48

エ

2.44

̶

2.41

 notor

2.38

USS

2.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.