INDEX

Explanations

terms related to political parties and their activities

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.02

2:0.09

3:0.06

4:0.05

5:0.03

6:0.41

7:0.04

8:0.06

9:0.04

10:0.07

11:0.05

Negative Logits

ESE

-1.44

��

-1.41

INAL

-1.40

ALSE

-1.35

omore

-1.33

inventoryQuantity

-1.31

 whence

-1.25

ּ

-1.22

AIN

-1.20

ICLE

-1.20

POSITIVE LOGITS

"}],"

1.44

merce

1.32

GIF

1.27

imes

1.26

fram

1.25

 Codec

1.24

 Surviv

1.22

 Plays

1.22

ć

1.19

 Productions

1.19

Activations Density 0.000%

terms related to political parties and their activities

No Known Activations