INDEX

Explanations

words related to the concept of wasting time

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

0:0.03

1:0.02

2:0.04

3:0.04

4:0.30

5:0.03

6:0.01

7:0.02

8:0.31

9:0.08

10:0.04

11:0.02

Negative Logits

SF

-1.58

ARA

-1.57

ENG

-1.54

hest

-1.47

 highs

-1.45

soDeliveryDate

-1.43

Ec

-1.43

Ka

-1.43

 beneficiary

-1.38

 ranges

-1.38

POSITIVE LOGITS

theless

1.51

amus

1.51

 virginity

1.47

 Wast

1.45

????????

1.44

████████

1.43

anwhile

1.42

 frivol

1.42

00000000

1.42

spo

1.38

Activations Density 0.003%

words related to the concept of wasting time

No Comments

No Known Activations