INDEX

Explanations

phrases related to risks, threats, and survival, particularly in a business or political context

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.04

1:0.03

2:0.23

3:0.05

4:0.13

5:0.06

6:0.02

7:0.02

8:0.08

9:0.18

10:0.06

11:0.03

Negative Logits

zzo

-1.52

angelo

-1.49

yip

-1.44

ussen

-1.42

aughty

-1.41

aucas

-1.39

ahan

-1.36

orah

-1.36

ortium

-1.35

Scot

-1.35

POSITIVE LOGITS

 Survival

1.59

 Survive

1.46

 mutants

1.44

 adaptations

1.38

 survival

1.36

 Vault

1.33

 microbes

1.33

 infiltration

1.30

 instincts

1.29

 immortality

1.29

Activations Density 0.006%

phrases related to risks, threats, and survival, particularly in a business or political context

No Comments

No Known Activations