INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

2:0.08

3:0.08

4:0.09

5:0.07

6:0.09

7:0.09

8:0.09

9:0.07

10:0.08

11:0.06

Negative Logits

ONSORED

-1.90

Newsletter

-1.54

izes

-1.54

lies

-1.46

imb

-1.44

ined

-1.44

Associated

-1.41

iciency

-1.40

cms

-1.39

ites

-1.37

POSITIVE LOGITS

 corrid

1.95

 Pengu

1.75

BuyableInstoreAndOnline

1.71

 horizont

1.66

 voic

1.57

 opio

1.56

DragonMagazine

1.55

 redes

1.46

uci

1.40

 challeng

1.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.