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

0:0.10

1:0.05

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.06

8:0.09

9:0.09

10:0.08

11:0.08

Negative Logits

 Reich

-1.55

 tread

-1.50

ovan

-1.50

 design

-1.48

 chic

-1.46

 Petro

-1.42

 marketing

-1.41

 McMahon

-1.41

 circa

-1.41

 Kamp

-1.39

POSITIVE LOGITS

Magikarp

1.75

ochond

1.52

Attach

1.49

 Centauri

1.49

Shot

1.46

 unpop

1.45

jac

1.43

istrates

1.42

gence

1.41

byss

1.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.