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

1:0.08

2:0.10

3:0.07

4:0.09

5:0.07

6:0.09

7:0.08

8:0.07

9:0.07

10:0.07

11:0.07

Negative Logits

 Pinterest

-1.87

auld

-1.78

 Hubbard

-1.68

 handwriting

-1.61

rero

-1.60

 Stab

-1.54

itated

-1.53

tery

-1.51

 Labrador

-1.51

Rye

-1.50

POSITIVE LOGITS

unless

1.97

 unless

1.95

externalActionCode

1.93

oppable

1.88

 outweigh

1.80

DragonMagazine

1.77

artifacts

1.76

ipeg

1.74

 fades

1.69

Unless

1.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.