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

1:0.06

2:0.08

3:0.08

4:0.08

5:0.08

6:0.09

7:0.07

8:0.10

9:0.08

10:0.07

11:0.07

Negative Logits

senal

-1.85

Benz

-1.75

ティ

-1.74

ディ

-1.72

OV

-1.67

-1.65

-1.63

 referen

-1.61

 refuel

-1.61

wine

-1.60

POSITIVE LOGITS

 reigning

1.86

 unworthy

1.82

 wealthier

1.76

 fashionable

1.74

 illustrious

1.73

 victorious

1.72

 deserving

1.71

 boom

1.70

 ugly

1.64

 injustice

1.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.