INDEX

Explanations

Russian names and words

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

proper nouns, particularly names of people and places

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

1:0.04

2:0.09

3:0.31

4:0.03

5:0.02

6:0.13

7:0.07

8:0.05

9:0.07

10:0.05

11:0.06

Negative Logits

idays

-1.18

$$$$

-1.17

manship

-1.13

wolves

-1.12

ascript

-1.12

··

-1.11

keepers

-1.09

blance

-1.09

rower

-1.08

yip

-1.08

POSITIVE LOGITS

 サーティワン

1.28

 Unch

1.26

 Glac

1.24

idis

1.19

 Fundamental

1.18

hene

1.16

 Verge

1.15

UGE

1.13

ミ

1.13

throp

1.09

Activations Density 0.006%

Russian names and words

proper nouns, particularly names of people and places

No Comments

No Known Activations