INDEX

Explanations

quoted speech or dialogue in the text

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.10

1:0.02

2:0.06

3:0.06

4:0.03

5:0.05

6:0.22

7:0.05

8:0.12

9:0.08

10:0.08

11:0.10

Negative Logits

ć

-1.30

 dominated

-1.28

cean

-1.27

 encomp

-1.26

 Ascension

-1.26

 glac

-1.25

heric

-1.24

emonic

-1.21

adjusted

-1.21

 methodological

-1.17

POSITIVE LOGITS

andise

1.63

laughs

1.55

earances

1.50

oji

1.50

twitter

1.36

potion

1.34

ashes

1.34

Attempts

1.33

Ability

1.33

%%%%

1.31

Activations Density 0.007%

quoted speech or dialogue in the text

No Comments

No Known Activations