INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.07

1:0.09

2:0.07

3:0.08

4:0.08

5:0.09

6:0.07

7:0.07

8:0.08

9:0.09

10:0.07

11:0.09

Negative Logits

 Triumph

-2.68

estern

-2.58

opened

-2.56

 Vaughan

-2.56

 Floyd

-2.51

 Evangel

-2.50

Hamilton

-2.48

 Lenn

-2.47

iannopoulos

-2.44

 Wynne

-2.43

POSITIVE LOGITS

 finer

2.66

 unnecess

2.45

amate

2.44

 derivatives

2.43

ames

2.39

sub

2.39

 functionally

2.35

bom

2.35

 trillions

2.32

FER

2.32

Activations Density 0.000%

No Known Activations

This feature has no known activations.