INDEX

Explanations

specific acronyms and abbreviations related to various topics

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

New Auto-Interp

Top Features by Cosine Similarity

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

2:0.11

3:0.30

4:0.03

5:0.02

6:0.13

7:0.06

8:0.06

9:0.04

10:0.10

11:0.04

Negative Logits

 fiat

-1.16

paw

-1.16

 decree

-1.09

eree

-1.07

asking

-1.06

glers

-1.02

ividual

-1.01

�

-1.00

icut

-1.00

 Venezuel

-0.99

POSITIVE LOGITS

��

1.27

aston

1.26

Bed

1.25

nikov

1.24

 Moroc

1.24

Û

1.23

hyde

1.22

pillar

1.21

��

1.17

��

1.17

Activations Density 0.032%

specific acronyms and abbreviations related to various topics

No Comments

No Known Activations