INDEX

Explanations

references to specific locations or entities, particularly those related to the MGM Grand

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

Head Attr Weights

0:0.03

1:0.04

2:0.09

3:0.22

4:0.02

5:0.03

6:0.15

7:0.08

8:0.03

9:0.11

10:0.08

11:0.07

Negative Logits

alion

-1.24

terday

-1.19

 charism

-1.17

sheet

-1.13

imov

-1.10

erto

-1.10

 solicitation

-1.09

STA

-1.06

acters

-1.05

 coli

-1.03

POSITIVE LOGITS

��

1.40

nih

1.22

rats

1.18

pees

1.08

ヘラ

1.08

intosh

1.08

roe

1.07

û

1.06

 Mansion

1.03

rient

1.03

Activations Density 0.003%

references to specific locations or entities, particularly those related to the MGM Grand

No Known Activations