INDEX

Explanations

questions directed towards someone's actions or intentions

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

0:0.07

1:0.02

2:0.07

3:0.19

4:0.19

5:0.04

6:0.05

7:0.02

8:0.14

9:0.06

10:0.06

11:0.03

Negative Logits

mone

-1.28

 tribe

-1.25

 Chev

-1.25

 laure

-1.24

allah

-1.23

pora

-1.22

Strong

-1.21

van

-1.20

Che

-1.20

 tree

-1.19

POSITIVE LOGITS

soever

1.66

?]

1.65

?'"

1.46

?'

1.45

HTTP

1.45

UFC

1.42

 Serie

1.40

(%)

1.38

kson

1.37

?」

1.37

Activations Density 0.039%

questions directed towards someone's actions or intentions

No Comments

No Known Activations