INDEX

Explanations

verbs related to perception and mental processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.04

1:0.02

2:0.12

3:0.08

4:0.10

5:0.02

6:0.23

7:0.17

8:0.03

9:0.05

10:0.07

11:0.04

Negative Logits

actionDate

-1.68

Ago

-1.64

eday

-1.59

abouts

-1.57

ム

-1.51

UTC

-1.50

ーン

-1.49

ellation

-1.47

Date

-1.44

dayName

-1.42

POSITIVE LOGITS

ANY

1.54

 thanking

1.41

 vain

1.40

atever

1.29

 SECTION

1.29

 acknow

1.27

 lest

1.26

 projecting

1.25

 slightest

1.25

 acquaint

1.24

Activations Density 0.001%

verbs related to perception and mental processes

No Comments

No Known Activations