INDEX

Explanations

phrases related to self-empowerment or self-reliance

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

phrases that indicate self-reference or self-identification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

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

0:0.01

1:0.02

2:0.17

3:0.04

4:0.01

5:0.06

6:0.19

7:0.15

8:0.09

9:0.06

10:0.08

11:0.06

Negative Logits

cussion

-1.05

microsoft

-0.99

の魔

-0.94

 mornings

-0.93

helm

-0.93

OPT

-0.89

 WARN

-0.88

gap

-0.86

LOT

-0.85

 Cull

-0.84

POSITIVE LOGITS

quished

0.97

aeus

0.94

its

0.93

 Jagu

0.93

 ancest

0.92

ワ

0.89

terday

0.87

ubuntu

0.87

aly

0.86

ipedia

0.85

Activations Density 0.031%

phrases related to self-empowerment or self-reliance

phrases that indicate self-reference or self-identification

No Comments

No Known Activations