INDEX

Explanations

references to times or locations in the context of 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

0:0.01

1:0.01

2:0.09

3:0.05

4:0.14

5:0.02

6:0.05

7:0.25

8:0.02

9:0.04

10:0.15

11:0.10

Negative Logits

 Cosponsors

-1.72

 perspectives

-1.56

ORPG

-1.54

 viewpoint

-1.51

icularly

-1.50

 outfits

-1.49

 endorsements

-1.46

 viewpoints

-1.43

 disproportion

-1.42

 quotes

-1.41

POSITIVE LOGITS

 awaiting

1.52

Memory

1.49

 heartbeat

1.48

 awake

1.46

eem

1.45

dh

1.45

 recovering

1.43

 asleep

1.41

 Recover

1.40

Dup

1.38

Activations Density 0.001%

references to times or locations in the context of events

No Comments

No Known Activations