INDEX

Explanations

quantitative data related to demographics and populations

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

0:0.01

1:0.04

2:0.11

3:0.04

4:0.02

5:0.04

6:0.05

7:0.13

8:0.32

9:0.11

10:0.03

11:0.06

Negative Logits

opian

-1.42

NPR

-1.26

rompt

-1.22

pload

-1.19

merce

-1.18

answer

-1.18

iphany

-1.18

 sanity

-1.16

ellig

-1.16

encing

-1.14

POSITIVE LOGITS

 Extras

1.32

 Others

1.19

Gou

1.19

 Hond

1.18

 Tradable

1.14

 Parish

1.12

 Salvador

1.11

 steroids

1.10

 Medals

1.10

 Percent

1.10

Activations Density 0.020%

quantitative data related to demographics and populations

No Comments

No Known Activations