INDEX

Explanations

phrases related to workplace issues and conflicts

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

1:0.02

2:0.08

3:0.05

4:0.04

5:0.04

6:0.04

7:0.10

8:0.19

9:0.06

10:0.18

11:0.10

Negative Logits

 demonstrating

-0.86

 confir

-0.86

 Bearing

-0.85

 outing

-0.83

 PayPal

-0.81

 Frazier

-0.81

 Fowler

-0.81

 Citation

-0.81

 Pratt

-0.80

 referring

-0.79

POSITIVE LOGITS

ドラ

1.08

Pokémon

1.02

=-=-=-=-=-=-=-=-

1.02

endas

1.00

hetics

0.99

thood

0.95

Quotes

0.95

Intern

0.93

Planet

0.90

ADVERTISEMENT

0.90

Activations Density 0.837%

phrases related to workplace issues and conflicts

No Comments

No Known Activations