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

0:0.09

1:0.07

2:0.09

3:0.08

4:0.07

5:0.08

6:0.09

7:0.07

8:0.09

9:0.06

10:0.09

11:0.08

Negative Logits

 Cance

-1.68

wcs

-1.57

ustomed

-1.56

oppers

-1.55

anwhile

-1.54

 Nanto

-1.54

ellen

-1.53

icio

-1.51

 Investments

-1.49

acebook

-1.49

POSITIVE LOGITS

cens

2.08

................................................................

1.99

AMY

1.73

wav

1.73

shall

1.70

bringer

1.66

onomy

1.63

natureconservancy

1.58

 Adren

1.56

idae

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.