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

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.08

3:0.08

4:0.09

5:0.09

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 pies

-1.94

 Emblem

-1.93

 territ

-1.77

 Vict

-1.72

lance

-1.71

 gloves

-1.71

 trophies

-1.70

luster

-1.64

 Stre

-1.64

 victories

-1.63

POSITIVE LOGITS

田

2.33

1.98

ahu

1.93

オ

1.86

�

1.85

 裏�

1.83

uckland

1.82

�士

1.80

龍�

1.80

�

1.78

Activations Density 0.000%

No Known Activations

This feature has no known activations.