INDEX

Explanations

references to political events and actions involving conflict and governance

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

0:0.04

1:0.02

2:0.08

3:0.07

4:0.07

5:0.08

6:0.06

7:0.38

8:0.05

9:0.02

10:0.03

11:0.05

Negative Logits

kaya

-2.71

 attRot

-2.68

rocal

-2.32

oya

-2.21

ript

-2.19

ibrarian

-2.18

amina

-2.16

izo

-2.16

tery

-2.15

 sexes

-2.15

POSITIVE LOGITS

his

5.41

His

5.02

His

4.91

his

4.82

 himself

4.49

HIS

4.46

He

4.26

he

4.21

He

4.06

him

4.02

Activations Density 0.185%

references to political events and actions involving conflict and governance

No Comments

No Known Activations