INDEX

Explanations

No Explanations Found

New Auto-Interp

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

0:0.05

1:0.05

2:0.10

3:0.07

4:0.12

5:0.09

6:0.09

7:0.09

8:0.08

9:0.07

10:0.06

11:0.07

Negative Logits

ozy

-1.49

 Gleaming

-1.44

 Extensions

-1.42

Weight

-1.37

 Nemesis

-1.35

 Destruction

-1.34

 Witch

-1.32

 Favorite

-1.30

Cool

-1.29

idable

-1.27

POSITIVE LOGITS

 hindsight

1.85

jury

1.69

edin

1.65

gans

1.64

�

1.56

DIT

1.46

nesota

1.46

sole

1.45

fman

1.43

 millisec

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.