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

1:0.05

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.09

8:0.09

9:0.07

10:0.08

11:0.07

Negative Logits

obyl

-2.11

DragonMagazine

-1.95

ebted

-1.88

 IMAGES

-1.80

utterstock

-1.75

IUM

-1.75

ongs

-1.72

ItemImage

-1.67

ombies

-1.65

andise

-1.65

POSITIVE LOGITS

 interfering

1.65

 cooperating

1.55

 responding

1.53

 electrom

1.50

 polyg

1.50

 loophole

1.49

 delaying

1.48

 regulating

1.48

 circuit

1.45

 diam

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.