INDEX

Explanations

phrases that indicate human actions or occurrences

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_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

0:0.02

1:0.03

2:0.08

3:0.05

4:0.07

5:0.03

6:0.35

7:0.13

8:0.03

9:0.03

10:0.06

11:0.06

Negative Logits

erest

-2.00

utra

-1.34

udo

-1.33

kefeller

-1.32

earch

-1.31

icut

-1.29

 Nose

-1.29

uably

-1.26

rimp

-1.25

 Navigation

-1.24

POSITIVE LOGITS

 looph

1.32

upon

1.24

 Interface

1.23

 inhabit

1.23

 milit

1.22

League

1.20

 ASCII

1.20

CLA

1.20

perties

1.19

 citiz

1.19

Activations Density 0.007%

phrases that indicate human actions or occurrences

No Comments

No Known Activations