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

0:0.07

1:0.05

2:0.09

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.10

11:0.08

Negative Logits

 caul

-2.01

 oneself

-1.85

agnetic

-1.82

 abras

-1.80

 Clicker

-1.72

heit

-1.71

 aeros

-1.60

 cryptoc

-1.58

 comet

-1.58

cav

-1.53

POSITIVE LOGITS

 redistributed

1.81

 legalized

1.63

 reserves

1.60

 reserved

1.57

license

1.51

 reserve

1.49

 unchanged

1.48

 declined

1.47

 awaiting

1.45

mand

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.