INDEX

Explanations

instances of software bugs or fixes

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

0:0.24

1:0.09

2:0.02

3:0.03

4:0.01

5:0.10

6:0.04

7:0.01

8:0.08

9:0.14

10:0.13

11:0.06

Negative Logits

sonian

-2.12

 bond

-1.49

inant

-1.48

mir

-1.47

 bonds

-1.41

cius

-1.41

 oneself

-1.39

 fools

-1.35

lan

-1.31

azeera

-1.30

POSITIVE LOGITS

Added

2.21

 Added

1.94

Removed

1.91

Changed

1.90

Released

1.87

Updated

1.78

 Released

1.78

 Changed

1.77

 Posted

1.71

 Killed

1.69

Activations Density 0.008%

instances of software bugs or fixes

No Comments

No Known Activations