INDEX

Explanations

references to specific academic and political contexts, including institutions and individuals influential in decision-making processes

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

0:0.04

1:0.15

2:0.08

3:0.03

4:0.10

5:0.08

6:0.11

7:0.06

8:0.09

9:0.06

10:0.09

11:0.07

Negative Logits

Tokens

-1.41

 traged

-1.33

 triv

-1.23

 beforehand

-1.20

)."

-1.17

ogether

-1.15

MpServer

-1.15

 Colomb

-1.14

 Tunis

-1.13

laughs

-1.11

POSITIVE LOGITS

yrics

1.54

reetings

1.53

 Posted

1.49

›

1.38

 Answer

1.24

Dear

1.24

pmwiki

1.23

 Introduction

1.19

·

1.16

..........

1.14

Activations Density 0.249%

references to specific academic and political contexts, including institutions and individuals influential in decision-making processes

No Comments

No Known Activations