INDEX

Explanations

information related to news articles and current events

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

phrases related to signing up for services or offers

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

2:0.13

3:0.22

4:0.01

5:0.03

6:0.05

7:0.12

8:0.05

9:0.18

10:0.08

11:0.05

Negative Logits

mith

-1.29

��

-1.17

wered

-1.17

 overshadowed

-1.17

heim

-1.15

uncture

-1.13

bern

-1.10

raph

-1.10

vert

-1.09

tsky

-1.09

POSITIVE LOGITS

 entit

1.18

 waivers

1.16

ESV

1.15

 iTunes

1.14

 Consent

1.13

 entitle

1.11

UE

1.08

 CentOS

1.07

Sequ

1.07

 Teams

1.06

Activations Density 0.008%

information related to news articles and current events

phrases related to signing up for services or offers

No Comments

No Known Activations