INDEX

Explanations

sequences that involve pasting different elements together or processing data in some way

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

0:0.06

1:0.03

2:0.16

3:0.08

4:0.08

5:0.05

6:0.03

7:0.04

8:0.16

9:0.16

10:0.06

11:0.03

Negative Logits

 plotted

-1.26

etheless

-1.24

 estates

-1.21

 warr

-1.20

 peripheral

-1.18

 conflicted

-1.14

 diminished

-1.14

��

-1.11

 favourable

-1.11

dfx

-1.09

POSITIVE LOGITS

ragon

1.50

urized

1.45

atche

1.41

Sov

1.35

imen

1.33

igham

1.32

illin

1.24

washing

1.24

ause

1.23

 grape

1.22

Activations Density 0.001%

sequences that involve pasting different elements together or processing data in some way

No Comments

No Known Activations