INDEX

Explanations

positive sentiments and praises related to a specific entity or individual

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_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.1.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

0:0.26

1:0.17

2:0.12

3:0.04

4:0.09

5:0.02

6:0.02

7:0.02

8:0.03

9:0.02

10:0.09

11:0.08

Negative Logits

 Cheong

-1.40

osterone

-1.34

arnaev

-1.28

ンジ

-1.27

orously

-1.27

alle

-1.25

Flag

-1.22

auga

-1.22

Bar

-1.20

 Chung

-1.17

POSITIVE LOGITS

 sake

2.79

 purposes

2.17

ummies

1.76

 purpose

1.50

 reasons

1.49

 reconstruction

1.35

vity

1.35

amen

1.35

 upkeep

1.33

 liking

1.32

Activations Density 0.864%

positive sentiments and praises related to a specific entity or individual

No Comments

No Known Activations