INDEX

Explanations

phrases indicating player performance metrics and statistics

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

0:0.02

1:0.01

2:0.12

3:0.06

4:0.31

5:0.03

6:0.04

7:0.09

8:0.04

9:0.04

10:0.13

11:0.06

Negative Logits

 Merchant

-1.68

 Conflict

-1.49

 Flavoring

-1.48

insula

-1.44

izza

-1.39

 Radiation

-1.35

 Merchants

-1.34

CRIP

-1.34

bill

-1.33

 Influence

-1.33

POSITIVE LOGITS

 everywhere

1.60

itably

1.48

 wherever

1.46

 scrimmage

1.42

 jams

1.38

fter

1.38

bably

1.30

 scrim

1.29

untarily

1.29

 Janeiro

1.27

Activations Density 0.011%

phrases indicating player performance metrics and statistics

No Comments

No Known Activations