INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 WARN

-3.23

 Administ

-3.07

Administ

-2.92

--------------------------------------------------------

-2.91

 Pres

-2.84

 Posted

-2.82

 Tune

-2.76

Edited

-2.70

 Judicial

-2.67

 colle

-2.67

POSITIVE LOGITS

 denomination

2.69

gor

2.58

 slot

2.50

ulkan

2.39

yen

2.38

 Samoa

2.35

iku

2.35

 condu

2.34

ivably

2.33

 bisexual

2.30

Activations Density 0.000%

No Known Activations

This feature has no known activations.