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

1:0.06

2:0.08

3:0.07

4:0.08

5:0.09

6:0.08

7:0.07

8:0.09

9:0.08

10:0.10

11:0.07

Negative Logits

 milestones

-1.76

 Sparrow

-1.66

 Raven

-1.64

 calendars

-1.60

 Vern

-1.57

 perman

-1.56

iae

-1.56

 independence

-1.54

 timeless

-1.53

 Grimm

-1.53

POSITIVE LOGITS

enum

2.06

perse

1.96

mid

1.88

activate

1.83

hyp

1.80

cmd

1.75

++)

1.71

eters

1.68

addons

1.68

pose

1.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.