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

2:0.07

3:0.08

4:0.07

5:0.09

6:0.07

7:0.08

8:0.09

9:0.07

10:0.08

11:0.09

Negative Logits

 Neck

-1.74

ong

-1.70

 Pompe

-1.65

 Mouth

-1.61

 Ground

-1.59

 Lung

-1.59

 Cruise

-1.57

LW

-1.55

 Chest

-1.55

uckles

-1.52

POSITIVE LOGITS

ウス

1.97

 ancest

1.91

izo

1.78

 millenn

1.76

 pestic

1.70

 dreaded

1.65

 fingerprint

1.65

 multiplication

1.62

BIL

1.60

 ingred

1.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.