INDEX

Explanations

mentions of political figures and their actions

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_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

Not in Any Lists

No Comments

Head Attr Weights

0:0.28

1:0.07

2:0.07

3:0.06

4:0.05

5:0.04

6:0.05

7:0.08

8:0.04

9:0.05

10:0.10

11:0.05

Negative Logits

 Lamar

-4.13

 Texans

-3.63

 Griffin

-3.39

Houston

-3.37

 Calvin

-3.23

 Harden

-3.22

 Dwight

-3.21

 Houston

-3.19

 Rockets

-3.16

 Canter

-3.12

POSITIVE LOGITS

 Lieberman

4.90

 Hoffman

4.31

ゴン

3.93

IE

3.46

microsoft

3.42

 Sweeney

3.34

 coff

3.32

ASA

3.27

 Dunk

3.26

Nep

3.22

Activations Density 0.003%

mentions of political figures and their actions

No Comments

No Known Activations