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

1:0.07

2:0.08

3:0.08

4:0.08

5:0.09

6:0.07

7:0.08

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

 negativity

-2.56

 Cancel

-2.53

cknow

-2.52

ondon

-2.50

 cance

-2.50

 denounce

-2.42

circle

-2.35

atown

-2.33

 discont

-2.32

ayson

-2.28

POSITIVE LOGITS

 Hawai

2.83

 iPod

2.72

Michigan

2.71

mi

2.71

 Michigan

2.70

 Spartan

2.63

 Idaho

2.51

idis

2.46

 Hispan

2.45

iPhone

2.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.