INDEX

Explanations

terms related to strict regulations and controls

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

2:0.09

3:0.08

4:0.03

5:0.04

6:0.08

7:0.16

8:0.04

9:0.04

10:0.07

11:0.26

Negative Logits

illions

-1.36

 Awakens

-1.28

etheus

-1.28

abilia

-1.24

nesota

-1.23

elaide

-1.17

igslist

-1.16

iverse

-1.12

esville

-1.11

ulz

-1.10

POSITIVE LOGITS

 restrictions

1.50

glers

1.39

 restrictive

1.38

rict

1.29

 regimes

1.29

 exceptions

1.29

 adherence

1.27

 requirements

1.27

 strict

1.26

 forbids

1.25

Activations Density 0.015%

terms related to strict regulations and controls

No Comments

No Known Activations