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

0:0.09

1:0.06

2:0.09

3:0.08

4:0.08

5:0.08

6:0.07

7:0.07

8:0.08

9:0.09

10:0.08

11:0.08

Negative Logits

deen

-2.11

eers

-1.83

avers

-1.83

furt

-1.81

 Fighters

-1.79

warts

-1.75

 hoops

-1.71

ostics

-1.68

illery

-1.66

 filib

-1.60

POSITIVE LOGITS

 ILCS

1.87

��

1.62

nan

1.62

 favourable

1.61

�

1.56

�

1.54

�

1.51

 heavenly

1.51

 favorable

1.49

OTAL

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.