INDEX

Explanations

words that suggest positivity or favorable conditions

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

0:0.03

1:0.04

2:0.08

3:0.33

4:0.03

5:0.02

6:0.08

7:0.10

8:0.04

9:0.06

10:0.07

11:0.07

Negative Logits

pole

-1.29

Bir

-1.19

Password

-1.13

otide

-1.13

chip

-1.12

assetsadobe

-1.05

agos

-1.04

IFF

-1.03

Spider

-1.02

Pref

-1.01

POSITIVE LOGITS

lishes

1.37

 Mormonism

1.28

 Mormons

1.20

emonium

1.10

Klu

1.09

BYU

1.09

ctory

1.08

ilst

1.08

redients

1.06

ESE

1.04

Activations Density 0.004%

words that suggest positivity or favorable conditions

No Comments

No Known Activations