INDEX

Explanations

instances of the word "of"

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

1:0.08

2:0.08

3:0.09

4:0.08

5:0.06

6:0.08

7:0.07

8:0.09

9:0.08

10:0.09

11:0.06

Negative Logits

 crow

-2.72

 uploaded

-2.71

 submissions

-2.71

 kicked

-2.57

 Guests

-2.54

 livestream

-2.51

 Frames

-2.48

 premie

-2.45

 bids

-2.37

 pals

-2.34

POSITIVE LOGITS

 Motorola

3.00

grain

2.83

AAA

2.67

Iowa

2.62

 Sioux

2.54

aukee

2.50

 Yugoslavia

2.48

iod

2.47

 vacc

2.45

antic

2.43

Activations Density 0.000%

instances of the word "of"

No Comments

No Known Activations