INDEX

Explanations

No Explanations Found

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

0:0.09

1:0.08

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.07

8:0.09

9:0.06

10:0.08

11:0.09

Negative Logits

 winding

-1.86

 increments

-1.81

maximum

-1.72

doi

-1.70

Lock

-1.70

 trough

-1.67

elsen

-1.63

 Current

-1.63

sequence

-1.60

slot

-1.59

POSITIVE LOGITS

 virginity

2.23

Magikarp

1.92

opausal

1.85

WARE

1.80

galitarian

1.80

 Niet

1.77

ali

1.73

 achie

1.73

 distingu

1.72

Reloaded

1.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.