INDEX

Explanations

specific quantities or measurements

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

numerical values and percentages related to statistics and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.09

1:0.02

2:0.24

3:0.10

4:0.03

5:0.08

6:0.03

7:0.06

8:0.05

9:0.07

10:0.11

11:0.06

Negative Logits

gha

-1.24

abeth

-1.17

quickShipAvailable

-1.13

 Cloak

-1.11

aucus

-1.11

imaru

-1.10

 Majesty

-1.08

anski

-1.08

 Religion

-1.08

ifier

-1.08

POSITIVE LOGITS

 apiece

1.53

ottest

1.42

bps

1.34

1.33

1.32

 consecutive

1.31

percent

1.30

million

1.27

automatic

1.25

lb

1.21

Activations Density 0.262%

specific quantities or measurements

numerical values and percentages related to statistics and measurements

No Comments

No Known Activations