INDEX

Explanations

discussions about risk factors and safety issues related to emergencies

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

0:0.02

1:0.02

2:0.05

3:0.04

4:0.01

5:0.04

6:0.07

7:0.21

8:0.05

9:0.02

10:0.06

11:0.34

Negative Logits

racuse

-1.55

rha

-1.54

ById

-1.49

ACTED

-1.46

untarily

-1.45

afety

-1.44

 counselling

-1.42

elaide

-1.40

 authorised

-1.32

OUP

-1.31

POSITIVE LOGITS

 tales

1.42

 imaginable

1.38

genre

1.33

folk

1.33

sounding

1.29

yet

1.27

 behold

1.26

 mortals

1.25

enance

1.23

 Scandinavian

1.22

Activations Density 0.640%

discussions about risk factors and safety issues related to emergencies

No Comments

No Known Activations