INDEX

Explanations

phrases related to speculative science and technological advancements, specifically focusing on particle physics and antimatter

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

terms related to particle physics and annihilation events

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

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

Head Attr Weights

0:0.08

1:0.09

2:0.09

3:0.08

4:0.06

5:0.09

6:0.06

7:0.07

8:0.07

9:0.09

10:0.09

11:0.09

Negative Logits

urance

-1.42

comfort

-1.40

eur

-1.39

hur

-1.38

stood

-1.38

 showc

-1.35

Ser

-1.31

raint

-1.31

ggles

-1.30

ylum

-1.29

POSITIVE LOGITS

═

1.62

 fucked

1.53

══

1.39

ICO

1.38

 lame

1.37

IZE

1.32

��

1.29

illet

1.29

 mascul

1.29

 moot

1.28

Activations Density 0.000%

phrases related to speculative science and technological advancements, specifically focusing on particle physics and antimatter

terms related to particle physics and annihilation events

No Known Activations