INDEX

Explanations

references to political and governmental actions regarding community welfare

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

1:0.04

2:0.04

3:0.05

4:0.06

5:0.08

6:0.04

7:0.07

8:0.02

9:0.41

10:0.03

11:0.06

Negative Logits

Prev

-2.54

ationally

-2.18

ibly

-2.03

helps

-2.00

qv

-2.00

undo

-1.96

wcsstore

-1.95

ト

-1.93

 Recomm

-1.90

Alert

-1.90

POSITIVE LOGITS

SPONSORED

2.39

 mobs

2.23

 cuisine

2.12

 billionaires

2.09

zsche

2.01

 runaway

2.00

 organised

1.98

 majorities

1.98

 slaves

1.96

 anarchists

1.93

Activations Density 0.176%

references to political and governmental actions regarding community welfare

No Known Activations