INDEX

Explanations

specific Eastern European names and cultural references

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.05

1:0.03

2:0.11

3:0.08

4:0.04

5:0.03

6:0.41

7:0.02

8:0.04

9:0.05

10:0.05

11:0.04

Negative Logits

acebook

-1.46

retty

-1.44

edIn

-1.37

ongyang

-1.34

yout

-1.33

natureconservancy

-1.32

ecause

-1.29

emouth

-1.29

zona

-1.29

ModLoader

-1.25

POSITIVE LOGITS

���

1.89

afort

1.43

amic

1.39

ilege

1.32

�

1.31

�

1.30

arching

1.24

ּ

1.24

ondo

1.21

 McGee

1.19

Activations Density 0.001%

specific Eastern European names and cultural references

No Comments

No Known Activations