INDEX

Explanations

parts of the text that indicate engagement with the content, such as likes or shares

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

1:0.02

2:0.16

3:0.04

4:0.09

5:0.02

6:0.23

7:0.18

8:0.04

9:0.05

10:0.05

11:0.04

Negative Logits

 Judicial

-1.48

 scheduling

-1.44

roma

-1.42

erning

-1.32

eln

-1.25

 mans

-1.24

 stopping

-1.23

 appointing

-1.22

jun

-1.18

 adjud

-1.17

POSITIVE LOGITS

 guiName

1.40

dayName

1.40

stories

1.38

[|

1.32

ideshow

1.31

 ILCS

1.29

erald

1.28

vez

1.27

 Saban

1.26

 attm

1.25

Activations Density 0.000%

parts of the text that indicate engagement with the content, such as likes or shares

No Comments

No Known Activations