INDEX

Explanations

terms related to accidents and fatalities involving vehicles

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

0:0.01

1:0.01

2:0.06

3:0.05

4:0.08

5:0.04

6:0.03

7:0.13

8:0.03

9:0.03

10:0.33

11:0.16

Negative Logits

 Patreon

-1.34

bern

-1.29

agall

-1.25

icons

-1.24

rir

-1.20

afort

-1.19

Democratic

-1.19

nah

-1.18

leground

-1.17

Pinterest

-1.17

POSITIVE LOGITS

 manslaughter

1.56

 accident

1.52

 Fatal

1.50

 Deaths

1.49

 fatal

1.46

 crashes

1.44

 motor

1.40

 roadside

1.37

 Died

1.31

 deaths

1.30

Activations Density 0.042%

terms related to accidents and fatalities involving vehicles

No Comments

No Known Activations