INDEX

Explanations

lists of countries and their relationships to each other

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

1:0.31

2:0.03

3:0.13

4:0.03

5:0.13

6:0.03

7:0.12

8:0.05

9:0.03

10:0.03

11:0.03

Negative Logits

abus

-2.73

eteria

-2.66

nah

-2.53

 shitty

-2.49

-2.47

atche

-2.46

-2.44

 lapt

-2.35

zsche

-2.35

 Warranty

-2.32

POSITIVE LOGITS

iless

2.90

 Moreno

2.77

��

2.75

 Libyan

2.48

heit

2.41

 Ezek

2.38

mite

2.38

STON

2.35

rity

2.35

 Kenyan

2.23

Activations Density 0.004%

lists of countries and their relationships to each other

No Comments

No Known Activations