INDEX

Explanations

dates and numerical values related to events

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

New Auto-Interp

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

0:0.02

1:0.01

2:0.18

3:0.16

4:0.12

5:0.03

6:0.04

7:0.07

8:0.04

9:0.06

10:0.07

11:0.14

Negative Logits

-1.53

FontSize

-1.44

 Oval

-1.35

CLASSIFIED

-1.34

 Glass

-1.34

 campuses

-1.33

 Dart

-1.31

 Goldstein

-1.28

 Gross

-1.27

 Abbey

-1.27

POSITIVE LOGITS

Ability

1.75

pci

1.45

itars

1.43

�

1.43

��

1.40

rael

1.40

death

1.38

utters

1.37

malink

1.35

 Allows

1.34

Activations Density 0.004%

dates and numerical values related to events

No Comments

No Known Activations