INDEX

Explanations

words associated with various forms of artistic expression

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

New Auto-Interp

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

2:0.05

3:0.06

4:0.05

5:0.04

6:0.46

7:0.03

8:0.04

9:0.07

10:0.07

11:0.05

Negative Logits

 Haram

-1.40

ink

-1.29

VW

-1.26

HF

-1.24

 itching

-1.23

 penn

-1.23

 streaks

-1.20

 bulls

-1.20

 mosquit

-1.19

 pets

-1.19

POSITIVE LOGITS

odus

1.66

DonaldTrump

1.65

aminer

1.59

arette

1.53

lished

1.52

inion

1.48

ptive

1.47

issance

1.46

endant

1.40

aptic

1.40

Activations Density 0.005%

words associated with various forms of artistic expression

No Comments

No Known Activations