INDEX

Explanations

phrases and terms related to seizing control or opportunity

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

0:0.02

1:0.00

2:0.07

3:0.05

4:0.15

5:0.02

6:0.12

7:0.37

8:0.02

9:0.02

10:0.05

11:0.06

Negative Logits

 Perspect

-1.48

iber

-1.39

iod

-1.39

ionage

-1.36

 stationed

-1.36

recomm

-1.36

ukemia

-1.35

ogue

-1.34

 trilogy

-1.34

isSpecialOrderable

-1.32

POSITIVE LOGITS

NetMessage

1.79

 levers

1.63

 hearts

1.61

 hips

1.57

 wheel

1.53

 palate

1.53

Catalog

1.48

 cart

1.47

 foothold

1.46

ヤ

1.45

Activations Density 0.007%

phrases and terms related to seizing control or opportunity

No Comments

No Known Activations