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

3:0.09

4:0.09

5:0.07

6:0.10

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

Reviewer

-1.81

dden

-1.71

 unaccount

-1.64

yss

-1.59

ographically

-1.57

 footing

-1.56

iffe

-1.55

ONE

-1.52

ayers

-1.50

steen

-1.49

POSITIVE LOGITS

 Cooking

1.85

ilet

1.76

 Hosp

1.64

 Wars

1.64

 Museum

1.53

dragon

1.52

gard

1.49

Chicken

1.49

 Fashion

1.48

 Roose

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.