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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.06

2:0.07

3:0.09

4:0.08

5:0.09

6:0.07

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

 Flavoring

-2.18

 Minor

-1.93

 Major

-1.73

 Students

-1.70

apego

-1.70

 Fighting

-1.67

 Chomsky

-1.63

 Moral

-1.63

========

-1.60

 Syri

-1.58

POSITIVE LOGITS

enegger

1.86

hoe

1.82

license

1.80

nan

1.76

Daddy

1.67

din

1.65

wine

1.63

vine

1.59

dam

1.58

web

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.