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

Head Attr Weights

0:0.09

1:0.05

2:0.10

3:0.07

4:0.09

5:0.08

6:0.08

7:0.09

8:0.07

9:0.08

10:0.08

11:0.07

Negative Logits

oppers

-1.91

udeb

-1.84

Wad

-1.73

 Advocate

-1.64

 organizers

-1.62

aceae

-1.57

 Operating

-1.53

 Opera

-1.53

ItemThumbnailImage

-1.52

 stumbled

-1.52

POSITIVE LOGITS

xon

2.07

coded

2.04

holm

1.94

assian

1.84

dain

1.78

oward

1.72

 dict

1.71

conn

1.70

ocument

1.70

auld

1.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.