INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.05

2:0.07

3:0.09

4:0.08

5:0.08

6:0.08

7:0.10

8:0.09

9:0.06

10:0.09

11:0.09

Negative Logits

WithNo

-1.88

Initialized

-1.59

cause

-1.57

-+-+

-1.56

ntil

-1.56

 Pastebin

-1.55

law

-1.54

 libel

-1.54

 Yourself

-1.53

ocide

-1.53

POSITIVE LOGITS

 yawn

1.68

 Borders

1.48

english

1.47

ythm

1.46

udeau

1.45

 sequ

1.43

externalActionCode

1.43

 Manila

1.41

ines

1.40

 negotiators

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.