INDEX

Explanations

references to structured data formats and related elements in technical writing

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

0:0.03

1:0.11

2:0.02

3:0.04

4:0.03

5:0.03

6:0.05

7:0.04

8:0.02

9:0.51

10:0.02

11:0.05

Negative Logits

Wil

-3.97

 Pupp

-3.54

 Julie

-3.48

Kun

-3.45

Mus

-3.44

Wil

-3.43

�

-3.35

 Wilkinson

-3.31

PP

-3.29

 Bowman

-3.27

POSITIVE LOGITS

6.16

5.78

 Twelve

4.94

 twelve

4.67

XII

4.22

3.99

3.91

elve

3.86

 Sail

3.65

3.44

Activations Density 0.034%

references to structured data formats and related elements in technical writing

No Comments

No Known Activations