INDEX

Explanations

No Explanations Found

New Auto-Interp

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

0:0.08

1:0.08

2:0.06

3:0.09

4:0.08

5:0.08

6:0.09

7:0.09

8:0.08

9:0.07

10:0.06

11:0.08

Negative Logits

 boundaries

-2.00

 independence

-1.73

 reperto

-1.69

 mafia

-1.64

 chores

-1.61

independence

-1.56

 autonomy

-1.54

 booze

-1.52

aeda

-1.51

 differe

-1.50

POSITIVE LOGITS

 Detected

1.71

aniel

1.67

lich

1.52

 embed

1.49

 Reve

1.42

 Shade

1.39

 Tweet

1.37

 Shop

1.36

York

1.36

 unearthed

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.