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

0:0.08

1:0.07

2:0.09

3:0.08

4:0.08

5:0.07

6:0.10

7:0.08

8:0.07

9:0.08

10:0.09

11:0.07

Negative Logits

VC

-2.94

rapnel

-2.89

ヴァ

-2.62

ESA

-2.61

 Hispan

-2.59

cients

-2.45

vre

-2.37

EStream

-2.37

unker

-2.36

emort

-2.34

POSITIVE LOGITS

 Tibetan

3.08

 Kash

3.01

ahi

2.71

 Kashmir

2.63

 Jude

2.58

agar

2.46

 Jewish

2.41

Tam

2.39

;;;;;;;;;;;;

2.39

inski

2.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.