INDEX

Explanations

instances of street or location identifiers

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

0:0.08

1:0.07

2:0.08

3:0.09

4:0.09

5:0.08

6:0.10

7:0.07

8:0.07

9:0.07

10:0.06

11:0.08

Negative Logits

 McKenzie

-2.81

 Bridges

-2.51

 James

-2.45

 Dove

-2.43

 joint

-2.41

 Warrant

-2.37

 CCTV

-2.34

 Goodman

-2.33

 RCMP

-2.32

 Berry

-2.28

POSITIVE LOGITS

ゴン

3.45

ptroller

3.01

azine

2.92

Pand

2.83

HTML

2.71

soDeliveryDate

2.69

============

2.68

========

2.68

覚醒

2.67

upload

2.66

Activations Density 0.000%

instances of street or location identifiers

No Comments

No Known Activations