INDEX

Explanations

instances of legal terms and phrases

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

0:0.01

1:0.02

2:0.10

3:0.24

4:0.02

5:0.01

6:0.05

7:0.11

8:0.06

9:0.16

10:0.07

11:0.09

Negative Logits

undo

-1.32

github

-1.27

hern

-1.27

angular

-1.26

herer

-1.25

here

-1.22

Tool

-1.21

comes

-1.21

iod

-1.20

reen

-1.20

POSITIVE LOGITS

 delinqu

1.31

 miscar

1.25

 plagiar

1.21

 cannibal

1.17

 blasphemy

1.13

 Eminem

1.11

 complicity

1.10

 WATCHED

1.10

 heresy

1.09

 dishon

1.09

Activations Density 0.005%

instances of legal terms and phrases

No Comments

No Known Activations