INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.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

1:0.08

2:0.08

3:0.08

4:0.10

5:0.07

6:0.07

7:0.08

8:0.09

9:0.07

10:0.09

11:0.07

Negative Logits

 coincidence

-1.44

id

-1.41

 Burr

-1.40

ials

-1.37

pic

-1.35

Kob

-1.35

Fas

-1.32

 tidal

-1.30

Tai

-1.29

 Schr

-1.29

POSITIVE LOGITS

anium

2.19

awa

2.18

 constitu

2.17

emale

2.12

 destro

2.06

 seiz

1.96

merce

1.94

avorite

1.90

thood

1.85

BuyableInstoreAndOnline

1.75

Activations Density 0.000%

No Known Activations

This feature has no known activations.