INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

2:0.09

3:0.08

4:0.09

5:0.08

6:0.07

7:0.07

8:0.08

9:0.06

10:0.08

11:0.08

Negative Logits

uesday

-1.52

 Tune

-1.47

izons

-1.43

eday

-1.41

rocket

-1.41

TED

-1.38

unes

-1.38

 Qualcomm

-1.34

×

-1.34

appropriately

-1.33

POSITIVE LOGITS

 complain

1.55

 Masquerade

1.53

 Cosmetic

1.51

 practise

1.49

 spirits

1.45

 paed

1.44

ocent

1.41

alion

1.39

 demoral

1.35

Commission

1.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.