INDEX

Explanations

phrases indicating the presence of specific items or components

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.05

1:0.03

2:0.20

3:0.04

4:0.22

5:0.06

6:0.02

7:0.03

8:0.05

9:0.18

10:0.04

11:0.02

Negative Logits

uthor

-1.58

illon

-1.43

usk

-1.34

ndra

-1.31

illac

-1.28

uesday

-1.23

estones

-1.22

 emanc

-1.21

vic

-1.20

alli

-1.20

POSITIVE LOGITS

 Blumenthal

1.46

 Gork

1.34

 Morty

1.29

 Nord

1.25

 Kell

1.23

 Kers

1.20

 Milo

1.16

Klu

1.15

 Katrina

1.15

riers

1.14

Activations Density 0.004%

phrases indicating the presence of specific items or components

No Comments

No Known Activations