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

0:0.06

1:0.05

2:0.08

3:0.09

4:0.08

5:0.08

6:0.07

7:0.07

8:0.07

9:0.09

10:0.10

11:0.10

Negative Logits

ulk

-1.68

urate

-1.59

Zub

-1.49

 "...

-1.41

Zac

-1.39

ighed

-1.38

Tol

-1.36

upon

-1.34

 noticeably

-1.33

 solvent

-1.32

POSITIVE LOGITS

cffffcc

1.71

soDeliveryDate

1.68

ÃÂ

1.66

ーテ

1.64

覚醒

1.63

mares

1.58

Haunted

1.58

din

1.53

rows

1.53

GoldMagikarp

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.