INDEX

Explanations

mentions of animals and related food items

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

0:0.02

1:0.03

2:0.04

3:0.03

4:0.04

5:0.03

6:0.45

7:0.04

8:0.03

9:0.04

10:0.12

11:0.07

Negative Logits

quickShipAvailable

-1.63

isSpecialOrderable

-1.60

 volunt

-1.54

龍�

-1.49

 horizont

-1.48

ascript

-1.41

FUL

-1.37

 Lauder

-1.36

 disclaimer

-1.34

catentry

-1.33

POSITIVE LOGITS

vae

1.55

ioned

1.53

spawn

1.42

neck

1.33

coat

1.33

oots

1.33

quez

1.30

 Rats

1.30

obl

1.29

bane

1.27

Activations Density 0.213%

mentions of animals and related food items

No Comments

No Known Activations