INDEX

Explanations

references to fundraising and support for various causes or campaigns

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

0:0.01

1:0.03

2:0.09

3:0.07

4:0.02

5:0.06

6:0.07

7:0.18

8:0.08

9:0.10

10:0.12

11:0.12

Negative Logits

Downloadha

-1.10

ople

-1.08

 inhabited

-1.05

inct

-1.00

ウス

-1.00

":"/

-0.99

lights

-0.98

�

-0.96

 scars

-0.96

 ling

-0.94

POSITIVE LOGITS

azon

1.17

 Patreon

1.14

 Cosponsors

1.13

achine

1.13

owship

1.10

 crowdfunding

1.05

SPR

1.05

iously

1.04

 frivol

1.04

enegger

1.01

Activations Density 0.006%

references to fundraising and support for various causes or campaigns

No Known Activations