INDEX

Explanations

phrases involving legal terms and definitions related to criminality

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

0:0.14

1:0.03

2:0.25

3:0.07

4:0.04

5:0.09

6:0.05

7:0.06

8:0.09

9:0.05

10:0.05

11:0.03

Negative Logits

 ambul

-3.22

housing

-2.88

TPPStreamerBot

-2.74

WB

-2.71

insured

-2.63

ァ

-2.62

 paramedics

-2.61

 childbirth

-2.60

 condoms

-2.57

ertility

-2.56

POSITIVE LOGITS

 espionage

6.06

 treason

5.98

 traitor

5.50

ionage

4.96

 treacher

4.80

 spies

4.53

 spying

4.21

spy

4.11

 Assass

3.65

 sabotage

3.64

Activations Density 0.001%

phrases involving legal terms and definitions related to criminality

No Comments

No Known Activations