INDEX

Explanations

phrases discussing self-perception and identity-related issues

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_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

0:0.06

1:0.02

2:0.29

3:0.06

4:0.04

5:0.07

6:0.19

7:0.01

8:0.07

9:0.03

10:0.03

11:0.09

Negative Logits

ipel

-1.46

izable

-1.40

 disparate

-1.38

parable

-1.36

IUM

-1.34

Weather

-1.32

 Annex

-1.32

ulence

-1.31

 Kits

-1.28

ATCH

-1.26

POSITIVE LOGITS

bley

1.75

ppard

1.59

kefeller

1.47

chu

1.47

agine

1.46

alone

1.43

inea

1.42

odka

1.42

ende

1.41

elong

1.41

Activations Density 0.037%

phrases discussing self-perception and identity-related issues

No Comments

No Known Activations