INDEX

Explanations

phrases related to periods of time

oai_token-act-pair · gpt-3.5-turbo 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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.03

2:0.13

3:0.07

4:0.24

5:0.06

6:0.03

7:0.04

8:0.07

9:0.13

10:0.05

11:0.02

Negative Logits

ocr

-1.41

 Quartz

-1.39

Nusra

-1.32

ogyn

-1.31

Mex

-1.30

IQ

-1.29

 Scrib

-1.28

Chem

-1.25

ween

-1.24

Mind

-1.23

POSITIVE LOGITS

 folds

1.35

 blows

1.32

imester

1.30

iatus

1.29

 prelim

1.29

 accrued

1.28

 fold

1.24

 innings

1.19

quo

1.18

 rotation

1.17

Activations Density 0.004%

phrases related to periods of time

No Comments

No Known Activations