INDEX

Explanations

terms related to life and death concepts along with their associated significance

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

2:0.07

3:0.04

4:0.06

5:0.03

6:0.42

7:0.05

8:0.02

9:0.03

10:0.11

11:0.09

Negative Logits

ibl

-1.52

etically

-1.44

allo

-1.38

yip

-1.37

icut

-1.36

ictive

-1.36

inyl

-1.36

xon

-1.31

mercial

-1.30

_-

-1.30

POSITIVE LOGITS

 anesthesia

1.20

 裏�

1.16

 deaf

1.13

 impression

1.08

�

1.08

 disse

1.07

 Challenger

1.07

 earthqu

1.07

 premier

1.06

 Levant

1.04

Activations Density 0.005%

terms related to life and death concepts along with their associated significance

No Comments

No Known Activations