INDEX

Explanations

phrases indicating consequences or implications

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

0:0.05

1:0.01

2:0.17

3:0.05

4:0.23

5:0.04

6:0.02

7:0.01

8:0.22

9:0.08

10:0.05

11:0.02

Negative Logits

started

-1.30

aqu

-1.21

Coh

-1.20

 screened

-1.17

Reviewed

-1.13

abee

-1.10

 largeDownload

-1.09

etheus

-1.09

seeking

-1.08

iste

-1.08

POSITIVE LOGITS

 disabling

1.40

ディ

1.39

 topp

1.24

kinson

1.23

 damages

1.22

osaurus

1.22

 ratification

1.21

 undo

1.20

 disadvant

1.17

rawdownloadcloneembedreportprint

1.15

Activations Density 0.032%

phrases indicating consequences or implications

No Comments

No Known Activations