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

0:0.07

1:0.06

2:0.09

3:0.08

4:0.09

5:0.08

6:0.08

7:0.10

8:0.08

9:0.07

10:0.07

11:0.09

Negative Logits

 ACTIONS

-1.67

 expired

-1.54

}"

-1.45

Dutch

-1.42

/)

-1.39

 Supplementary

-1.37

Copyright

-1.36

 remaining

-1.35

AFP

-1.34

я

-1.34

POSITIVE LOGITS

ndra

1.64

 Inher

1.64

iuses

1.59

 mathemat

1.59

 adore

1.53

 sugg

1.53

iao

1.52

tut

1.51

ichen

1.51

 envy

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.