INDEX

Explanations

discussions about democracy and its functionalities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.13

1:0.02

2:0.21

3:0.09

4:0.04

5:0.07

6:0.08

7:0.08

8:0.08

9:0.09

10:0.04

11:0.02

Negative Logits

 Ranger

-3.39

Ski

-3.17

catentry

-3.13

FH

-3.13

 heater

-3.00

inventory

-2.94

 Bears

-2.91

 Loft

-2.91

 Adapter

-2.91

ュ

-2.89

POSITIVE LOGITS

 democracy

7.62

 democracies

7.52

democracy

7.27

 democratic

7.18

 Democracy

6.95

democratic

6.54

 Democr

6.49

 democratically

6.25

 democr

6.21

 democrat

5.77

Activations Density 0.069%

discussions about democracy and its functionalities

No Comments

No Known Activations