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

1:0.08

2:0.08

3:0.07

4:0.08

5:0.07

6:0.08

7:0.07

8:0.07

9:0.08

10:0.09

11:0.09

Negative Logits

 Serge

-2.82

YC

-2.77

iannopoulos

-2.50

ACC

-2.46

arro

-2.40

Rac

-2.40

 Aman

-2.38

 Salam

-2.34

 Aram

-2.33

DEN

-2.31

POSITIVE LOGITS

schild

2.85

advertising

2.70

 reader

2.61

 waterproof

2.48

alling

2.41

 whopping

2.40

 campaigner

2.37

 ladies

2.36

 feather

2.33

 streng

2.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.