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

0:0.08

1:0.06

2:0.08

3:0.08

4:0.09

5:0.07

6:0.09

7:0.09

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

 Jericho

-1.57

ilight

-1.47

 Bunker

-1.38

 Survival

-1.34

 Siege

-1.34

 Bella

-1.32

 filib

-1.29

 Leonardo

-1.27

 originally

-1.27

inventoryQuantity

-1.26

POSITIVE LOGITS

appointed

1.64

looking

1.59

ordinate

1.58

xus

1.58

wcs

1.55

 unaccount

1.51

 ACTIONS

1.50

sounding

1.47

ciples

1.46

verages

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.