INDEX

Explanations

phrases indicating levels, dimensions, or aspects of measurement and evaluation

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

0:0.02

1:0.02

2:0.20

3:0.07

4:0.02

5:0.03

6:0.14

7:0.09

8:0.03

9:0.02

10:0.05

11:0.26

Negative Logits

eri

-1.21

ersive

-1.20

ickers

-1.20

iets

-1.17

icks

-1.14

ected

-1.13

aleb

-1.12

ainment

-1.12

icked

-1.12

eln

-1.11

POSITIVE LOGITS

 imaginable

2.53

 conceivable

1.88

 except

1.71

 whatsoever

1.71

except

1.62

 mathemat

1.40

 possible

1.40

 nodd

1.36

 besides

1.31

 aspect

1.29

Activations Density 0.041%

phrases indicating levels, dimensions, or aspects of measurement and evaluation

No Comments

No Known Activations