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

1:0.07

2:0.08

3:0.07

4:0.08

5:0.08

6:0.08

7:0.09

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

aples

-1.95

vale

-1.83

opathic

-1.78

zees

-1.77

icides

-1.76

galitarian

-1.76

 ingred

-1.75

 mathemat

-1.74

 Flavoring

-1.73

 kindred

-1.68

POSITIVE LOGITS

Thumbnail

1.76

ケ

1.75

Untitled

1.73

 intercepted

1.72

 photograph

1.70

PHOTOS

1.66

Publisher

1.64

 photographed

1.61

 screenshot

1.59

png

1.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.