INDEX

Explanations

terms related to processing and understanding information

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_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

2:0.18

3:0.06

4:0.15

5:0.06

6:0.03

7:0.02

8:0.11

9:0.17

10:0.06

11:0.02

Negative Logits

usra

-1.38

inka

-1.33

ulet

-1.30

hawks

-1.30

kamp

-1.29

ozyg

-1.29

inguished

-1.20

orney

-1.17

chuk

-1.14

azeera

-1.14

POSITIVE LOGITS

 digest

1.93

 Digest

1.64

 digestion

1.60

 multiplication

1.32

 Travels

1.27

VERTISEMENT

1.24

 Flavoring

1.24

Characters

1.24

 filler

1.23

 consumes

1.19

Activations Density 0.003%

terms related to processing and understanding information

No Comments

No Known Activations