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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.09

2:0.08

3:0.09

4:0.07

5:0.08

6:0.07

7:0.08

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

VK

-2.78

 Ember

-2.53

 Torment

-2.52

 Patton

-2.48

ELE

-2.34

 Kick

-2.34

 Mighty

-2.31

�

-2.30

orb

-2.29

TRI

-2.24

POSITIVE LOGITS

 mathemat

2.64

ationally

2.55

atown

2.53

 Synd

2.52

assian

2.50

Sensor

2.50

iod

2.42

 segreg

2.41

 Lect

2.41

NEC

2.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.