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

0:0.08

1:0.08

2:0.09

3:0.07

4:0.09

5:0.07

6:0.09

7:0.08

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

say

-1.65

 duplication

-1.51

grave

-1.44

 patiently

-1.40

together

-1.39

turned

-1.38

 sequ

-1.33

 forwarded

-1.31

 bott

-1.30

 gloom

-1.30

POSITIVE LOGITS

odynamics

1.65

ako

1.60

asio

1.59

VID

1.55

bard

1.46

 TAMADRA

1.44

esson

1.44

antz

1.41

adin

1.40

ergic

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.