INDEX

Explanations

elements related to law enforcement, community dynamics, or geographic attributes in various contexts

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

1:0.01

2:0.24

3:0.14

4:0.10

5:0.03

6:0.07

7:0.04

8:0.04

9:0.07

10:0.13

11:0.05

Negative Logits

 Catalyst

-1.62

 Argon

-1.41

 Slater

-1.40

 conclud

-1.38

 intervening

-1.37

[*

-1.33

[[

-1.32

 narrowed

-1.28

 nerves

-1.27

ayson

-1.27

POSITIVE LOGITS

ヘラ

1.81

�

1.73

channelAvailability

1.58

�

1.53

fail

1.52

MSN

1.51

lov

1.50

json

1.49

��

1.41

ugu

1.41

Activations Density 0.019%

elements related to law enforcement, community dynamics, or geographic attributes in various contexts

No Comments

No Known Activations