INDEX

Explanations

terms related to financial instruments and regulatory procedures

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

keywords and terms related to finance and investment strategies

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.04

1:0.02

2:0.16

3:0.12

4:0.02

5:0.09

6:0.04

7:0.06

8:0.05

9:0.18

10:0.13

11:0.05

Negative Logits

 Entered

-1.64

姫

-1.33

advertising

-1.26

ギ

-1.14

天

-1.11

 Seraph

-1.07

CLASSIFIED

-1.06

Justice

-1.05

zek

-1.02

 acknow

-1.02

POSITIVE LOGITS

 itself

1.93

ciation

1.35

glers

1.31

alone

1.20

reciation

1.19

eatures

1.19

istries

1.17

olicy

1.17

owder

1.17

 Brewers

1.15

Activations Density 1.040%

terms related to financial instruments and regulatory procedures

keywords and terms related to finance and investment strategies

No Comments

No Known Activations