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

0:0.09

1:0.07

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.09

8:0.07

9:0.08

10:0.06

11:0.08

Negative Logits

 Torrent

-2.89

 Vessel

-2.68

 Patron

-2.67

Torrent

-2.64

 Flavoring

-2.63

 Taxi

-2.62

 Morse

-2.61

netflix

-2.56

 Fellow

-2.53

 Firefly

-2.49

POSITIVE LOGITS

 stockp

2.74

�

2.71

 ther

2.66

wra

2.62

 doct

2.55

 floor

2.49

�

2.43

 chopping

2.43

vacc

2.42

washing

2.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.