INDEX

Explanations

phrases indicating the act of cutting or reducing something

New Auto-Interp

Top Features by Cosine Similarity

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

Head Attr Weights

0:0.04

1:0.01

2:0.26

3:0.10

4:0.07

5:0.04

6:0.02

7:0.02

8:0.22

9:0.12

10:0.03

11:0.02

Negative Logits

ONSORED

-1.48

SPONSORED

-1.31

��

-1.25

iott

-1.24

��

-1.22

 Directorate

-1.13

sbm

-1.11

 Lowry

-1.09

yne

-1.08

 Lowe

-1.08

POSITIVE LOGITS

thro

1.71

 noses

1.45

unct

1.32

 teeth

1.30

bones

1.26

 chin

1.24

ument

1.21

 coffin

1.20

�

1.20

 bass

1.20

Activations Density 0.028%

phrases indicating the act of cutting or reducing something

No Known Activations