INDEX

Explanations

phrases related to financial and technological topics

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

phrases that indicate likelihood or probability

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

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

1:0.03

2:0.12

3:0.27

4:0.02

5:0.03

6:0.07

7:0.12

8:0.06

9:0.04

10:0.11

11:0.07

Negative Logits

 Peaks

-1.24

 Moor

-1.18

 resemblance

-1.14

 Mahar

-1.10

Constructed

-1.04

utor

-1.04

PW

-1.03

 Kali

-1.00

Vu

-0.99

Vet

-0.97

POSITIVE LOGITS

etheless

1.44

ructose

1.18

insula

1.15

azeera

1.11

aneously

1.10

apon

1.08

amaru

1.07

normal

1.06

pace

1.06

cape

1.04

Activations Density 0.007%

phrases related to financial and technological topics

phrases that indicate likelihood or probability

No Comments

No Known Activations