INDEX

Explanations

references to gaming mechanics or concepts

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

0:0.11

1:0.05

2:0.09

3:0.10

4:0.09

5:0.07

6:0.06

7:0.05

8:0.07

9:0.09

10:0.11

11:0.07

Negative Logits

arnaev

-1.62

 perished

-1.50

 Vide

-1.49

tains

-1.47

oples

-1.38

 population

-1.37

 correlates

-1.37

abase

-1.33

DERR

-1.33

 correlated

-1.31

POSITIVE LOGITS

 diplomacy

1.56

robe

1.52

 Blessing

1.50

Haunted

1.47

 Empress

1.42

 gardening

1.42

 discretion

1.40

 opera

1.39

choice

1.38

paren

1.37

Activations Density 0.000%

references to gaming mechanics or concepts

No Comments

No Known Activations