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

1:0.08

2:0.08

3:0.08

4:0.09

5:0.07

6:0.08

7:0.10

8:0.06

9:0.08

10:0.08

11:0.07

Negative Logits

Hew

-1.90

 Metro

-1.80

 Commodore

-1.68

 Jagu

-1.66

 Atari

-1.65

 Holo

-1.54

 Pinterest

-1.52

 Bern

-1.51

 GeForce

-1.51

 Abrams

-1.51

POSITIVE LOGITS

Hunt

1.91

sonian

1.86

ItemThumbnailImage

1.78

iary

1.78

veyard

1.63

 confir

1.63

milo

1.63

inator

1.62

emetery

1.56

ecycle

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.