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

0:0.09

1:0.05

2:0.09

3:0.07

4:0.09

5:0.08

6:0.07

7:0.09

8:0.08

9:0.06

10:0.09

11:0.09

Negative Logits

FAM

-1.90

 Instr

-1.87

inis

-1.86

 separ

-1.84

family

-1.81

 Integ

-1.79

ulic

-1.77

 Families

-1.73

Bus

-1.70

 entrances

-1.67

POSITIVE LOGITS

ascript

1.69

 imaginable

1.68

INGTON

1.57

 warrant

1.56

MSM

1.56

 fool

1.55

 peeled

1.55

erity

1.54

 Investor

1.53

asel

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.