INDEX

Explanations

references to specific locations or directions within a given space

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

0:0.04

1:0.04

2:0.09

3:0.04

4:0.04

5:0.13

6:0.03

7:0.03

8:0.06

9:0.32

10:0.08

11:0.04

Negative Logits

anmar

-1.44

yip

-1.37

pac

-1.28

apego

-1.24

abama

-1.22

IRA

-1.20

 Afgh

-1.20

iband

-1.18

alions

-1.17

psons

-1.17

POSITIVE LOGITS

 floors

1.48

 Hatch

1.35

tyard

1.29

 Eisen

1.22

 ceilings

1.16

 ventilation

1.16

 protr

1.15

 halls

1.15

ural

1.14

Sty

1.14

Activations Density 0.028%

references to specific locations or directions within a given space

No Comments

No Known Activations