INDEX

Explanations

mentions of accountability or misleading 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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.03

2:0.07

3:0.07

4:0.15

5:0.05

6:0.05

7:0.22

8:0.05

9:0.07

10:0.08

11:0.09

Negative Logits

Dial

-1.59

ーク

-1.53

olean

-1.40

Constructed

-1.38

ة

-1.35

ンジ

-1.31

Sit

-1.31

ه

-1.29

ザ

-1.26

iciary

-1.26

POSITIVE LOGITS

Loading

1.38

 endorsements

1.29

 assignments

1.28

 Abilities

1.26

 envelop

1.26

 NOTICE

1.24

 Frozen

1.21

Age

1.20

age

1.19

 Terms

1.19

Activations Density 0.000%

mentions of accountability or misleading actions

No Comments

No Known Activations