INDEX

Explanations

adjectives that describe emotional or physical states, as well as verbs related to negative or self-destructive actions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.06

1:0.04

2:0.25

3:0.03

4:0.31

5:0.04

6:0.03

7:0.02

8:0.07

9:0.04

10:0.05

11:0.03

Negative Logits

オ

-1.63

Interstitial

-1.51

icip

-1.44

endment

-1.38

ş

-1.38

leep

-1.35

inarily

-1.34

expected

-1.32

isites

-1.31

isite

-1.31

POSITIVE LOGITS

 Commodore

1.43

 Marriott

1.32

�

1.27

EStream

1.27

 Ballard

1.24

 Seymour

1.23

 Clubs

1.22

 PowerShell

1.22

NES

1.22

��

1.21

Activations Density 0.029%

adjectives that describe emotional or physical states, as well as verbs related to negative or self-destructive actions

No Comments

No Known Activations