INDEX

Explanations

actions and events related to gathering, urgency, or changes in situations

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

1:0.09

2:0.05

3:0.09

4:0.05

5:0.03

6:0.05

7:0.40

8:0.04

9:0.04

10:0.03

11:0.05

Negative Logits

 Clarke

-2.71

 unden

-2.66

Random

-2.42

 Random

-2.40

 Braun

-2.32

-2.29

alian

-2.28

alle

-2.27

 amino

-2.27

Lin

-2.25

POSITIVE LOGITS

wcs

3.00

cott

2.92

iw

2.78

kees

2.67

ivas

2.48

 Morg

2.48

 Piet

2.42

SourceFile

2.41

cape

2.41

MGM

2.37

Activations Density 0.005%

actions and events related to gathering, urgency, or changes in situations

No Comments

No Known Activations