INDEX

Explanations

references to relationships and connections between people or entities

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_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

0:0.01

1:0.01

2:0.10

3:0.05

4:0.32

5:0.03

6:0.04

7:0.23

8:0.03

9:0.03

10:0.05

11:0.05

Negative Logits

effic

-1.84

ulence

-1.66

efficiency

-1.62

 favorably

-1.54

eness

-1.45

adish

-1.45

 topping

-1.44

 repr

-1.41

erity

-1.41

ppings

-1.35

POSITIVE LOGITS

igers

1.50

gov

1.40

 Biol

1.40

 Refugees

1.38

 Administ

1.34

Les

1.34

DonaldTrump

1.33

 Ryder

1.30

alde

1.29

axis

1.29

Activations Density 0.017%

references to relationships and connections between people or entities

No Comments

No Known Activations