INDEX

Explanations

phrases and words related to measurement and comparison

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

Head Attr Weights

0:0.02

1:0.01

2:0.06

3:0.06

4:0.14

5:0.03

6:0.05

7:0.33

8:0.04

9:0.04

10:0.10

11:0.06

Negative Logits

trak

-1.67

ItemImage

-1.52

黒

-1.44

BuyableInstoreAndOnline

-1.41

ダ

-1.41

 buck

-1.39

acious

-1.37

フォ

-1.34

 overdoses

-1.34

 Tank

-1.34

POSITIVE LOGITS

 Immunity

1.72

 Priv

1.63

 citizenship

1.61

 kins

1.59

 Relations

1.56

laws

1.55

 confidentiality

1.55

eer

1.54

thur

1.51

 competence

1.48

Activations Density 0.000%

phrases and words related to measurement and comparison

No Known Activations