INDEX

Explanations

fragments related to technology and printing processes

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

0:0.37

1:0.01

2:0.10

3:0.08

4:0.02

5:0.09

6:0.05

7:0.04

8:0.05

9:0.08

10:0.03

11:0.02

Negative Logits

 Awoken

-2.75

 Offense

-2.62

wcsstore

-2.54

Netflix

-2.50

 playlist

-2.44

Season

-2.40

Nid

-2.39

��

-2.34

 Ranking

-2.33

youtube

-2.31

POSITIVE LOGITS

 printing

7.59

 printers

7.09

 printer

7.00

 Printing

6.77

 print

6.54

Print

6.34

 printed

6.06

 prints

6.01

 Print

5.88

print

5.77

Activations Density 0.073%

fragments related to technology and printing processes

No Comments

No Known Activations